niobures commited on
Commit
fb689a6
·
verified ·
1 Parent(s): dab2794

Chatterbox TTS (en-onnx, ru, pt, multi)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. en/onnx/chatterbox-onnx/.gitattributes +38 -0
  3. en/onnx/chatterbox-onnx/conditional_decoder.onnx +3 -0
  4. en/onnx/chatterbox-onnx/conds.pt +3 -0
  5. en/onnx/chatterbox-onnx/flow_inference.onnx +3 -0
  6. en/onnx/chatterbox-onnx/hift_generator.onnx +3 -0
  7. en/onnx/chatterbox-onnx/llama_with_past.onnx +3 -0
  8. en/onnx/chatterbox-onnx/onnx/language_model.onnx +3 -0
  9. en/onnx/chatterbox-onnx/onnx/language_model.onnx_data +3 -0
  10. en/onnx/chatterbox-onnx/source.txt +1 -0
  11. en/onnx/chatterbox-onnx/speech_embedding.onnx +3 -0
  12. en/onnx/chatterbox-onnx/speech_encoder.onnx +3 -0
  13. en/onnx/chatterbox-onnx/stft_wrapper.onnx +3 -0
  14. en/onnx/chatterbox-onnx/tokenizer.json +1435 -0
  15. en/onnx/chatterbox-onnx/tokenizer_config.json +2061 -0
  16. en/onnx/chatterbox-onnx/vc_tokenizer_weights.pth +3 -0
  17. en/onnx/chatterbox_ONNX/.gitattributes +37 -0
  18. en/onnx/chatterbox_ONNX/conditional_decoder.onnx +3 -0
  19. en/onnx/chatterbox_ONNX/flow_inference.onnx +3 -0
  20. en/onnx/chatterbox_ONNX/llama3.data +3 -0
  21. en/onnx/chatterbox_ONNX/llama3.onnx +3 -0
  22. en/onnx/chatterbox_ONNX/source.txt +1 -0
  23. en/onnx/chatterbox_ONNX/speech_encoder.onnx +3 -0
  24. en/onnx/chatterbox_ONNX/tokenizer.json +1435 -0
  25. en/onnx/chatterbox_ONNX/tokenizer_config.json +2061 -0
  26. multi/expanded_chatterbox_model/.gitattributes +35 -0
  27. multi/expanded_chatterbox_model/conds.pt +3 -0
  28. multi/expanded_chatterbox_model/s3gen.safetensors +3 -0
  29. multi/expanded_chatterbox_model/source.txt +1 -0
  30. multi/expanded_chatterbox_model/t3_cfg.safetensors +3 -0
  31. multi/expanded_chatterbox_model/tokenizer.json +2458 -0
  32. multi/expanded_chatterbox_model/ve.safetensors +3 -0
  33. pt/Chatterbox-TTS-Portuguese/.gitattributes +35 -0
  34. pt/Chatterbox-TTS-Portuguese/README.md +34 -0
  35. pt/Chatterbox-TTS-Portuguese/conds.pt +3 -0
  36. pt/Chatterbox-TTS-Portuguese/s3gen.safetensors +3 -0
  37. pt/Chatterbox-TTS-Portuguese/source.txt +1 -0
  38. pt/Chatterbox-TTS-Portuguese/t3_cfg.safetensors +3 -0
  39. pt/Chatterbox-TTS-Portuguese/tokenizer.json +1435 -0
  40. pt/Chatterbox-TTS-Portuguese/ve.safetensors +3 -0
  41. ru/Chatterbox-Russian-TTS/.gitattributes +35 -0
  42. ru/Chatterbox-Russian-TTS/source.txt +1 -0
  43. ru/Chatterbox-Russian-TTS/t3_cfg_16000_steps.safetensors +3 -0
  44. ru/Chatterbox-Russian-TTS/tokenizer.json +1735 -0
  45. ru/chatterbox-ru-t3k/.gitattributes +35 -0
  46. ru/chatterbox-ru-t3k/all_results.json +11 -0
  47. ru/chatterbox-ru-t3k/checkpoint-1200/model.safetensors +3 -0
  48. ru/chatterbox-ru-t3k/checkpoint-1200/optimizer.pt +3 -0
  49. ru/chatterbox-ru-t3k/checkpoint-1200/rng_state.pth +3 -0
  50. ru/chatterbox-ru-t3k/checkpoint-1200/scheduler.pt +3 -0
.gitattributes CHANGED
@@ -66,3 +66,5 @@ no/samples/Arnulf[[:space:]]Overland[[:space:]]-[[:space:]]08_05_07[[:space:]]-[
66
  no/samples/Arnulf[[:space:]]Overland[[:space:]]-[[:space:]]12_05_07[[:space:]]-[[:space:]]Male.wav filter=lfs diff=lfs merge=lfs -text
67
  no/samples/Arnulf[[:space:]]Overland[[:space:]]-[[:space:]]13_05_04[[:space:]]-[[:space:]]Female.wav filter=lfs diff=lfs merge=lfs -text
68
  no/samples/Ibsens[[:space:]]Ripsbaerbursker.wav filter=lfs diff=lfs merge=lfs -text
 
 
 
66
  no/samples/Arnulf[[:space:]]Overland[[:space:]]-[[:space:]]12_05_07[[:space:]]-[[:space:]]Male.wav filter=lfs diff=lfs merge=lfs -text
67
  no/samples/Arnulf[[:space:]]Overland[[:space:]]-[[:space:]]13_05_04[[:space:]]-[[:space:]]Female.wav filter=lfs diff=lfs merge=lfs -text
68
  no/samples/Ibsens[[:space:]]Ripsbaerbursker.wav filter=lfs diff=lfs merge=lfs -text
69
+ en/onnx/chatterbox_ONNX/llama3.data filter=lfs diff=lfs merge=lfs -text
70
+ en/onnx/chatterbox-onnx/onnx/language_model.onnx_data filter=lfs diff=lfs merge=lfs -text
en/onnx/chatterbox-onnx/.gitattributes ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ llama3.onnx.data filter=lfs diff=lfs merge=lfs -text
37
+ llama3.data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/language_model.onnx_data filter=lfs diff=lfs merge=lfs -text
en/onnx/chatterbox-onnx/conditional_decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcac4d92bed1fc493ed9615c2c951885f052156daae18680e2685bae6b18ddf8
3
+ size 286352231
en/onnx/chatterbox-onnx/conds.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6552d70568833628ba019c6b03459e77fe71ca197d5c560cef9411bee9d87f4e
3
+ size 107374
en/onnx/chatterbox-onnx/flow_inference.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de5f4a45e8e89788956e1374cdf67f561019d40480bab3942513e6b81259d0f4
3
+ size 185816292
en/onnx/chatterbox-onnx/hift_generator.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c186efb97d260555584f00baa97c6e009d0d0335a60b40f2fc15ffaa68527ee
3
+ size 70304704
en/onnx/chatterbox-onnx/llama_with_past.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96957a58b7ebf1a5bd5322949637dd6e040f1377a0686b5bef1fcd1e176016b
3
+ size 2047725936
en/onnx/chatterbox-onnx/onnx/language_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2f908a1062e3ff40e11d9d59c2580af4407ae9734186901afc43942fc67b19
3
+ size 228474
en/onnx/chatterbox-onnx/onnx/language_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a91e4d9d3d8eb948913f18bca4b08d2b40fca553a33181c03d80d84c090c63
3
+ size 2080632832
en/onnx/chatterbox-onnx/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/onnx-community/chatterbox-onnx
en/onnx/chatterbox-onnx/speech_embedding.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c6935a267bbdada1b95b028659f0c582a9797901b9290d6cf9ca940f185008
3
+ size 50357075
en/onnx/chatterbox-onnx/speech_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd24809a8d265e7237a7d3e60104c38cd46eefa1621e7224583401d26d15388
3
+ size 79678497
en/onnx/chatterbox-onnx/stft_wrapper.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73cd386decc96dc65e2e43a6ad2b603d6792f3aae11bb9ccacbd3f294b5a0e34
3
+ size 13186298
en/onnx/chatterbox-onnx/tokenizer.json ADDED
@@ -0,0 +1,1435 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "special": true,
9
+ "content": "[STOP]",
10
+ "single_word": false,
11
+ "lstrip": false,
12
+ "rstrip": false,
13
+ "normalized": false
14
+ },
15
+ {
16
+ "id": 1,
17
+ "special": true,
18
+ "content": "[UNK]",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false
23
+ },
24
+ {
25
+ "id": 2,
26
+ "special": true,
27
+ "content": "[SPACE]",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false
32
+ },
33
+ {
34
+ "id": 255,
35
+ "special": true,
36
+ "content": "[START]",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false
41
+ },
42
+ {
43
+ "id": 604,
44
+ "content": "[UH]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 605,
53
+ "content": "[UM]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 606,
62
+ "content": "[giggle]",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 607,
71
+ "content": "[laughter]",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 608,
80
+ "content": "[guffaw]",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 609,
89
+ "content": "[inhale]",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 610,
98
+ "content": "[exhale]",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 611,
107
+ "content": "[sigh]",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 612,
116
+ "content": "[cry]",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 613,
125
+ "content": "[bark]",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 614,
134
+ "content": "[howl]",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 615,
143
+ "content": "[meow]",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 616,
152
+ "content": "[singing]",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 617,
161
+ "content": "[music]",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 618,
170
+ "content": "[whistle]",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 619,
179
+ "content": "[humming]",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 620,
188
+ "content": "[gasp]",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 621,
197
+ "content": "[groan]",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 622,
206
+ "content": "[whisper]",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 623,
215
+ "content": "[mumble]",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 624,
224
+ "content": "[sniff]",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 625,
233
+ "content": "[sneeze]",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 626,
242
+ "content": "[cough]",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 627,
251
+ "content": "[snore]",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 628,
260
+ "content": "[chew]",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 629,
269
+ "content": "[sip]",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 630,
278
+ "content": "[clear_throat]",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 631,
287
+ "content": "[kiss]",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 632,
296
+ "content": "[shhh]",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 633,
305
+ "content": "[gibberish]",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 634,
314
+ "content": "[fr]",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 635,
323
+ "content": "[es]",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 636,
332
+ "content": "[de]",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 637,
341
+ "content": "[it]",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 638,
350
+ "content": "[ipa]",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 639,
359
+ "content": "[end_of_label]",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 695,
368
+ "content": "[PLACEHOLDER55]",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 696,
377
+ "content": "[PLACEHOLDER56]",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 697,
386
+ "content": "[PLACEHOLDER57]",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 698,
395
+ "content": "[PLACEHOLDER58]",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 699,
404
+ "content": "[PLACEHOLDER59]",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 700,
413
+ "content": "[PLACEHOLDER60]",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 701,
422
+ "content": "[PLACEHOLDER61]",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 702,
431
+ "content": "[PLACEHOLDER62]",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 703,
440
+ "content": "[PLACEHOLDER63]",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ }
447
+ ],
448
+ "normalizer": null,
449
+ "pre_tokenizer": {
450
+ "type": "Whitespace"
451
+ },
452
+ "post_processor": null,
453
+ "decoder": null,
454
+ "model": {
455
+ "type": "BPE",
456
+ "dropout": null,
457
+ "unk_token": "[UNK]",
458
+ "continuing_subword_prefix": null,
459
+ "end_of_word_suffix": null,
460
+ "fuse_unk": false,
461
+ "vocab": {
462
+ "[STOP]": 0,
463
+ "[UNK]": 1,
464
+ "[SPACE]": 2,
465
+ "!": 3,
466
+ "'": 4,
467
+ "(": 5,
468
+ ")": 6,
469
+ ",": 7,
470
+ "-": 8,
471
+ ".": 9,
472
+ "/": 10,
473
+ ":": 11,
474
+ ";": 12,
475
+ "?": 13,
476
+ "a": 14,
477
+ "b": 15,
478
+ "c": 16,
479
+ "d": 17,
480
+ "e": 18,
481
+ "f": 19,
482
+ "g": 20,
483
+ "h": 21,
484
+ "i": 22,
485
+ "j": 23,
486
+ "k": 24,
487
+ "l": 25,
488
+ "m": 26,
489
+ "n": 27,
490
+ "o": 28,
491
+ "p": 29,
492
+ "q": 30,
493
+ "r": 31,
494
+ "s": 32,
495
+ "t": 33,
496
+ "u": 34,
497
+ "v": 35,
498
+ "w": 36,
499
+ "x": 37,
500
+ "y": 38,
501
+ "z": 39,
502
+ "th": 40,
503
+ "in": 41,
504
+ "the": 42,
505
+ "an": 43,
506
+ "er": 44,
507
+ "ou": 45,
508
+ "re": 46,
509
+ "on": 47,
510
+ "at": 48,
511
+ "ed": 49,
512
+ "en": 50,
513
+ "to": 51,
514
+ "ing": 52,
515
+ "and": 53,
516
+ "is": 54,
517
+ "as": 55,
518
+ "al": 56,
519
+ "or": 57,
520
+ "of": 58,
521
+ "ar": 59,
522
+ "it": 60,
523
+ "es": 61,
524
+ "he": 62,
525
+ "st": 63,
526
+ "le": 64,
527
+ "om": 65,
528
+ "se": 66,
529
+ "be": 67,
530
+ "ad": 68,
531
+ "ow": 69,
532
+ "ly": 70,
533
+ "ch": 71,
534
+ "wh": 72,
535
+ "that": 73,
536
+ "you": 74,
537
+ "li": 75,
538
+ "ve": 76,
539
+ "ac": 77,
540
+ "ti": 78,
541
+ "ld": 79,
542
+ "me": 80,
543
+ "was": 81,
544
+ "gh": 82,
545
+ "id": 83,
546
+ "ll": 84,
547
+ "wi": 85,
548
+ "ent": 86,
549
+ "for": 87,
550
+ "ay": 88,
551
+ "ro": 89,
552
+ "ver": 90,
553
+ "ic": 91,
554
+ "her": 92,
555
+ "ke": 93,
556
+ "his": 94,
557
+ "no": 95,
558
+ "ut": 96,
559
+ "un": 97,
560
+ "ir": 98,
561
+ "lo": 99,
562
+ "we": 100,
563
+ "ri": 101,
564
+ "ha": 102,
565
+ "with": 103,
566
+ "ght": 104,
567
+ "out": 105,
568
+ "im": 106,
569
+ "ion": 107,
570
+ "all": 108,
571
+ "ab": 109,
572
+ "one": 110,
573
+ "ne": 111,
574
+ "ge": 112,
575
+ "ould": 113,
576
+ "ter": 114,
577
+ "mo": 115,
578
+ "had": 116,
579
+ "ce": 117,
580
+ "she": 118,
581
+ "go": 119,
582
+ "sh": 120,
583
+ "ur": 121,
584
+ "am": 122,
585
+ "so": 123,
586
+ "pe": 124,
587
+ "my": 125,
588
+ "de": 126,
589
+ "are": 127,
590
+ "but": 128,
591
+ "ome": 129,
592
+ "fr": 130,
593
+ "ther": 131,
594
+ "fe": 132,
595
+ "su": 133,
596
+ "do": 134,
597
+ "con": 135,
598
+ "te": 136,
599
+ "ain": 137,
600
+ "ere": 138,
601
+ "po": 139,
602
+ "if": 140,
603
+ "they": 141,
604
+ "us": 142,
605
+ "ag": 143,
606
+ "tr": 144,
607
+ "now": 145,
608
+ "oun": 146,
609
+ "this": 147,
610
+ "have": 148,
611
+ "not": 149,
612
+ "sa": 150,
613
+ "il": 151,
614
+ "up": 152,
615
+ "thing": 153,
616
+ "from": 154,
617
+ "ap": 155,
618
+ "him": 156,
619
+ "ack": 157,
620
+ "ation": 158,
621
+ "ant": 159,
622
+ "our": 160,
623
+ "op": 161,
624
+ "like": 162,
625
+ "ust": 163,
626
+ "ess": 164,
627
+ "bo": 165,
628
+ "ok": 166,
629
+ "ul": 167,
630
+ "ind": 168,
631
+ "ex": 169,
632
+ "com": 170,
633
+ "some": 171,
634
+ "there": 172,
635
+ "ers": 173,
636
+ "co": 174,
637
+ "res": 175,
638
+ "man": 176,
639
+ "ard": 177,
640
+ "pl": 178,
641
+ "wor": 179,
642
+ "way": 180,
643
+ "tion": 181,
644
+ "fo": 182,
645
+ "ca": 183,
646
+ "were": 184,
647
+ "by": 185,
648
+ "ate": 186,
649
+ "pro": 187,
650
+ "ted": 188,
651
+ "ound": 189,
652
+ "own": 190,
653
+ "would": 191,
654
+ "ts": 192,
655
+ "what": 193,
656
+ "qu": 194,
657
+ "ally": 195,
658
+ "ight": 196,
659
+ "ck": 197,
660
+ "gr": 198,
661
+ "when": 199,
662
+ "ven": 200,
663
+ "can": 201,
664
+ "ough": 202,
665
+ "ine": 203,
666
+ "end": 204,
667
+ "per": 205,
668
+ "ous": 206,
669
+ "od": 207,
670
+ "ide": 208,
671
+ "know": 209,
672
+ "ty": 210,
673
+ "very": 211,
674
+ "si": 212,
675
+ "ak": 213,
676
+ "who": 214,
677
+ "about": 215,
678
+ "ill": 216,
679
+ "them": 217,
680
+ "est": 218,
681
+ "red": 219,
682
+ "ye": 220,
683
+ "could": 221,
684
+ "ong": 222,
685
+ "your": 223,
686
+ "their": 224,
687
+ "em": 225,
688
+ "just": 226,
689
+ "other": 227,
690
+ "into": 228,
691
+ "any": 229,
692
+ "whi": 230,
693
+ "um": 231,
694
+ "tw": 232,
695
+ "ast": 233,
696
+ "der": 234,
697
+ "did": 235,
698
+ "ie": 236,
699
+ "been": 237,
700
+ "ace": 238,
701
+ "ink": 239,
702
+ "ity": 240,
703
+ "back": 241,
704
+ "ting": 242,
705
+ "br": 243,
706
+ "more": 244,
707
+ "ake": 245,
708
+ "pp": 246,
709
+ "then": 247,
710
+ "sp": 248,
711
+ "el": 249,
712
+ "use": 250,
713
+ "bl": 251,
714
+ "said": 252,
715
+ "over": 253,
716
+ "get": 254,
717
+ "[START]": 255,
718
+ "\"": 256,
719
+ "#": 257,
720
+ "$": 258,
721
+ "%": 259,
722
+ "&": 260,
723
+ "*": 261,
724
+ "+": 262,
725
+ "0": 263,
726
+ "1": 264,
727
+ "2": 265,
728
+ "3": 266,
729
+ "4": 267,
730
+ "5": 268,
731
+ "6": 269,
732
+ "7": 270,
733
+ "8": 271,
734
+ "9": 272,
735
+ "<": 273,
736
+ "=": 274,
737
+ ">": 275,
738
+ "@": 276,
739
+ "A": 277,
740
+ "B": 278,
741
+ "C": 279,
742
+ "D": 280,
743
+ "E": 281,
744
+ "F": 282,
745
+ "G": 283,
746
+ "H": 284,
747
+ "I": 285,
748
+ "J": 286,
749
+ "K": 287,
750
+ "L": 288,
751
+ "M": 289,
752
+ "N": 290,
753
+ "O": 291,
754
+ "P": 292,
755
+ "Q": 293,
756
+ "R": 294,
757
+ "S": 295,
758
+ "T": 296,
759
+ "U": 297,
760
+ "V": 298,
761
+ "W": 299,
762
+ "X": 300,
763
+ "Y": 301,
764
+ "Z": 302,
765
+ "[": 303,
766
+ "\\": 304,
767
+ "]": 305,
768
+ "^": 306,
769
+ "_": 307,
770
+ "`": 308,
771
+ "{": 309,
772
+ "|": 310,
773
+ "}": 311,
774
+ "~": 312,
775
+ "‐": 313,
776
+ "‑": 314,
777
+ "‒": 315,
778
+ "–": 316,
779
+ "—": 317,
780
+ "―": 318,
781
+ "‖": 319,
782
+ "‗": 320,
783
+ "‘": 321,
784
+ "’": 322,
785
+ "‚": 323,
786
+ "‛": 324,
787
+ "“": 325,
788
+ "”": 326,
789
+ "„": 327,
790
+ "‟": 328,
791
+ " ": 329,
792
+ "¡": 330,
793
+ "¢": 331,
794
+ "£": 332,
795
+ "¤": 333,
796
+ "¥": 334,
797
+ "¦": 335,
798
+ "§": 336,
799
+ "¨": 337,
800
+ "©": 338,
801
+ "ª": 339,
802
+ "«": 340,
803
+ "¬": 341,
804
+ "­": 342,
805
+ "®": 343,
806
+ "¯": 344,
807
+ "°": 345,
808
+ "±": 346,
809
+ "²": 347,
810
+ "³": 348,
811
+ "´": 349,
812
+ "µ": 350,
813
+ "¶": 351,
814
+ "·": 352,
815
+ "¸": 353,
816
+ "¹": 354,
817
+ "º": 355,
818
+ "»": 356,
819
+ "¼": 357,
820
+ "½": 358,
821
+ "¾": 359,
822
+ "¿": 360,
823
+ "À": 361,
824
+ "Á": 362,
825
+ "Â": 363,
826
+ "Ã": 364,
827
+ "Ä": 365,
828
+ "Å": 366,
829
+ "Æ": 367,
830
+ "Ç": 368,
831
+ "È": 369,
832
+ "É": 370,
833
+ "Ê": 371,
834
+ "Ë": 372,
835
+ "Ì": 373,
836
+ "Í": 374,
837
+ "Î": 375,
838
+ "Ï": 376,
839
+ "Ð": 377,
840
+ "Ñ": 378,
841
+ "Ò": 379,
842
+ "Ó": 380,
843
+ "Ô": 381,
844
+ "Õ": 382,
845
+ "Ö": 383,
846
+ "×": 384,
847
+ "Ø": 385,
848
+ "Ù": 386,
849
+ "Ú": 387,
850
+ "Û": 388,
851
+ "Ü": 389,
852
+ "Ý": 390,
853
+ "Þ": 391,
854
+ "ß": 392,
855
+ "à": 393,
856
+ "á": 394,
857
+ "â": 395,
858
+ "ã": 396,
859
+ "ä": 397,
860
+ "å": 398,
861
+ "æ": 399,
862
+ "ç": 400,
863
+ "è": 401,
864
+ "é": 402,
865
+ "ê": 403,
866
+ "ë": 404,
867
+ "ì": 405,
868
+ "í": 406,
869
+ "î": 407,
870
+ "ï": 408,
871
+ "ð": 409,
872
+ "ñ": 410,
873
+ "ò": 411,
874
+ "ó": 412,
875
+ "ô": 413,
876
+ "õ": 414,
877
+ "ö": 415,
878
+ "÷": 416,
879
+ "ø": 417,
880
+ "ù": 418,
881
+ "ú": 419,
882
+ "û": 420,
883
+ "ü": 421,
884
+ "ý": 422,
885
+ "þ": 423,
886
+ "ÿ": 424,
887
+ "ɐ": 425,
888
+ "ɑ": 426,
889
+ "ɒ": 427,
890
+ "ɓ": 428,
891
+ "ɔ": 429,
892
+ "ɕ": 430,
893
+ "ɖ": 431,
894
+ "ɗ": 432,
895
+ "ɘ": 433,
896
+ "ə": 434,
897
+ "ɚ": 435,
898
+ "ɛ": 436,
899
+ "ɜ": 437,
900
+ "ɝ": 438,
901
+ "ɞ": 439,
902
+ "ɟ": 440,
903
+ "ɠ": 441,
904
+ "ɡ": 442,
905
+ "ɢ": 443,
906
+ "ɣ": 444,
907
+ "ɤ": 445,
908
+ "ɥ": 446,
909
+ "ɦ": 447,
910
+ "ɧ": 448,
911
+ "ɨ": 449,
912
+ "ɩ": 450,
913
+ "ɪ": 451,
914
+ "ɫ": 452,
915
+ "ɬ": 453,
916
+ "ɭ": 454,
917
+ "ɮ": 455,
918
+ "ɯ": 456,
919
+ "ɰ": 457,
920
+ "ɱ": 458,
921
+ "ɲ": 459,
922
+ "ɳ": 460,
923
+ "ɴ": 461,
924
+ "ɵ": 462,
925
+ "ɶ": 463,
926
+ "ɷ": 464,
927
+ "ɸ": 465,
928
+ "ɹ": 466,
929
+ "ɺ": 467,
930
+ "ɻ": 468,
931
+ "ɼ": 469,
932
+ "ɽ": 470,
933
+ "ɾ": 471,
934
+ "ɿ": 472,
935
+ "ʀ": 473,
936
+ "ʁ": 474,
937
+ "ʂ": 475,
938
+ "ʃ": 476,
939
+ "ʄ": 477,
940
+ "ʅ": 478,
941
+ "ʆ": 479,
942
+ "ʇ": 480,
943
+ "ʈ": 481,
944
+ "ʉ": 482,
945
+ "ʊ": 483,
946
+ "ʋ": 484,
947
+ "ʌ": 485,
948
+ "ʍ": 486,
949
+ "ʎ": 487,
950
+ "ʏ": 488,
951
+ "ʐ": 489,
952
+ "ʑ": 490,
953
+ "ʒ": 491,
954
+ "ʓ": 492,
955
+ "ʔ": 493,
956
+ "ʕ": 494,
957
+ "ʖ": 495,
958
+ "ʗ": 496,
959
+ "ʘ": 497,
960
+ "ʙ": 498,
961
+ "ʚ": 499,
962
+ "ʛ": 500,
963
+ "ʜ": 501,
964
+ "ʝ": 502,
965
+ "ʞ": 503,
966
+ "ʟ": 504,
967
+ "ʠ": 505,
968
+ "ʡ": 506,
969
+ "ʢ": 507,
970
+ "ʣ": 508,
971
+ "ʤ": 509,
972
+ "ʥ": 510,
973
+ "ʦ": 511,
974
+ "ʧ": 512,
975
+ "ʨ": 513,
976
+ "ʩ": 514,
977
+ "ʪ": 515,
978
+ "ʫ": 516,
979
+ "ʬ": 517,
980
+ "ʭ": 518,
981
+ "ʮ": 519,
982
+ "ʯ": 520,
983
+ "ʰ": 521,
984
+ "ʱ": 522,
985
+ "ʲ": 523,
986
+ "ʳ": 524,
987
+ "ʴ": 525,
988
+ "ʵ": 526,
989
+ "ʶ": 527,
990
+ "ʷ": 528,
991
+ "ʸ": 529,
992
+ "ʹ": 530,
993
+ "ʺ": 531,
994
+ "ʻ": 532,
995
+ "ʼ": 533,
996
+ "ʽ": 534,
997
+ "ʾ": 535,
998
+ "ʿ": 536,
999
+ "ˀ": 537,
1000
+ "ˁ": 538,
1001
+ "˂": 539,
1002
+ "˃": 540,
1003
+ "˄": 541,
1004
+ "˅": 542,
1005
+ "ˆ": 543,
1006
+ "ˇ": 544,
1007
+ "ˈ": 545,
1008
+ "ˉ": 546,
1009
+ "ˊ": 547,
1010
+ "ˋ": 548,
1011
+ "ˌ": 549,
1012
+ "ˍ": 550,
1013
+ "ˎ": 551,
1014
+ "ˏ": 552,
1015
+ "ː": 553,
1016
+ "ˑ": 554,
1017
+ "˒": 555,
1018
+ "˓": 556,
1019
+ "˔": 557,
1020
+ "˕": 558,
1021
+ "˖": 559,
1022
+ "˗": 560,
1023
+ "˘": 561,
1024
+ "˙": 562,
1025
+ "˚": 563,
1026
+ "˛": 564,
1027
+ "˜": 565,
1028
+ "˝": 566,
1029
+ "˞": 567,
1030
+ "˟": 568,
1031
+ "ˠ": 569,
1032
+ "ˡ": 570,
1033
+ "ˢ": 571,
1034
+ "ˣ": 572,
1035
+ "ˤ": 573,
1036
+ "˥": 574,
1037
+ "˦": 575,
1038
+ "˧": 576,
1039
+ "˨": 577,
1040
+ "˩": 578,
1041
+ "˪": 579,
1042
+ "˫": 580,
1043
+ "ˬ": 581,
1044
+ "˭": 582,
1045
+ "ˮ": 583,
1046
+ "˯": 584,
1047
+ "˰": 585,
1048
+ "˱": 586,
1049
+ "˲": 587,
1050
+ "˳": 588,
1051
+ "˴": 589,
1052
+ "˵": 590,
1053
+ "˶": 591,
1054
+ "˷": 592,
1055
+ "˸": 593,
1056
+ "˹": 594,
1057
+ "˺": 595,
1058
+ "˻": 596,
1059
+ "˼": 597,
1060
+ "˽": 598,
1061
+ "˾": 599,
1062
+ "˿": 600,
1063
+ "ā": 601,
1064
+ "ō": 602,
1065
+ "…": 603,
1066
+ "[UH]": 604,
1067
+ "[UM]": 605,
1068
+ "[giggle]": 606,
1069
+ "[laughter]": 607,
1070
+ "[guffaw]": 608,
1071
+ "[inhale]": 609,
1072
+ "[exhale]": 610,
1073
+ "[sigh]": 611,
1074
+ "[cry]": 612,
1075
+ "[bark]": 613,
1076
+ "[howl]": 614,
1077
+ "[meow]": 615,
1078
+ "[singing]": 616,
1079
+ "[music]": 617,
1080
+ "[whistle]": 618,
1081
+ "[humming]": 619,
1082
+ "[gasp]": 620,
1083
+ "[groan]": 621,
1084
+ "[whisper]": 622,
1085
+ "[mumble]": 623,
1086
+ "[sniff]": 624,
1087
+ "[sneeze]": 625,
1088
+ "[cough]": 626,
1089
+ "[snore]": 627,
1090
+ "[chew]": 628,
1091
+ "[sip]": 629,
1092
+ "[clear_throat]": 630,
1093
+ "[kiss]": 631,
1094
+ "[shhh]": 632,
1095
+ "[gibberish]": 633,
1096
+ "[fr]": 634,
1097
+ "[es]": 635,
1098
+ "[de]": 636,
1099
+ "[it]": 637,
1100
+ "[ipa]": 638,
1101
+ "[end_of_label]": 639,
1102
+ "ŋ": 640,
1103
+ "ᵻ": 641,
1104
+ "θ": 642,
1105
+ "̩": 643,
1106
+ "\u0303": 644,
1107
+ "ɑː": 645,
1108
+ "iː": 646,
1109
+ "uː": 647,
1110
+ "ɜː": 648,
1111
+ "ɔː": 649,
1112
+ "oː": 650,
1113
+ "eɪ": 651,
1114
+ "oʊ": 652,
1115
+ "aɪ": 653,
1116
+ "aʊ": 654,
1117
+ "ɔɪ": 655,
1118
+ "dʒ": 656,
1119
+ "tʃ": 657,
1120
+ "ɪŋ": 658,
1121
+ "ᵻd": 659,
1122
+ "ˈiː": 660,
1123
+ "ˌiː": 661,
1124
+ "ˈɪ": 662,
1125
+ "ˌɪ": 663,
1126
+ "ˈeɪ": 664,
1127
+ "ˌeɪ": 665,
1128
+ "ˈɛ": 666,
1129
+ "ˌɛ": 667,
1130
+ "ˈæ": 668,
1131
+ "ˌæ": 669,
1132
+ "ˈɑː": 670,
1133
+ "ˌɑː": 671,
1134
+ "ˈɔː": 672,
1135
+ "ˌɔː": 673,
1136
+ "oːɹ": 674,
1137
+ "ˈoːɹ": 675,
1138
+ "ˌoːɹ": 676,
1139
+ "ˈoʊ": 677,
1140
+ "ˌoʊ": 678,
1141
+ "ˈʊ": 679,
1142
+ "ˌʊ": 680,
1143
+ "ˈuː": 681,
1144
+ "ˌuː": 682,
1145
+ "ˈɜː": 683,
1146
+ "ˌɜː": 684,
1147
+ "ˈʌ": 685,
1148
+ "ˌʌ": 686,
1149
+ "ˈaɪ": 687,
1150
+ "ˌaɪ": 688,
1151
+ "ˈaʊ": 689,
1152
+ "ˌaʊ": 690,
1153
+ "ˈɔɪ": 691,
1154
+ "ˌɔɪ": 692,
1155
+ "ˈɚ": 693,
1156
+ "ˌɐ": 694,
1157
+ "[PLACEHOLDER55]": 695,
1158
+ "[PLACEHOLDER56]": 696,
1159
+ "[PLACEHOLDER57]": 697,
1160
+ "[PLACEHOLDER58]": 698,
1161
+ "[PLACEHOLDER59]": 699,
1162
+ "[PLACEHOLDER60]": 700,
1163
+ "[PLACEHOLDER61]": 701,
1164
+ "[PLACEHOLDER62]": 702,
1165
+ "[PLACEHOLDER63]": 703
1166
+ },
1167
+ "merges": [
1168
+ "t h",
1169
+ "i n",
1170
+ "th e",
1171
+ "a n",
1172
+ "e r",
1173
+ "o u",
1174
+ "r e",
1175
+ "o n",
1176
+ "a t",
1177
+ "e d",
1178
+ "e n",
1179
+ "t o",
1180
+ "in g",
1181
+ "an d",
1182
+ "i s",
1183
+ "a s",
1184
+ "a l",
1185
+ "o r",
1186
+ "o f",
1187
+ "a r",
1188
+ "i t",
1189
+ "e s",
1190
+ "h e",
1191
+ "s t",
1192
+ "l e",
1193
+ "o m",
1194
+ "s e",
1195
+ "b e",
1196
+ "a d",
1197
+ "o w",
1198
+ "l y",
1199
+ "c h",
1200
+ "w h",
1201
+ "th at",
1202
+ "y ou",
1203
+ "l i",
1204
+ "v e",
1205
+ "a c",
1206
+ "t i",
1207
+ "l d",
1208
+ "m e",
1209
+ "w as",
1210
+ "g h",
1211
+ "i d",
1212
+ "l l",
1213
+ "w i",
1214
+ "en t",
1215
+ "f or",
1216
+ "a y",
1217
+ "r o",
1218
+ "v er",
1219
+ "i c",
1220
+ "h er",
1221
+ "k e",
1222
+ "h is",
1223
+ "n o",
1224
+ "u t",
1225
+ "u n",
1226
+ "i r",
1227
+ "l o",
1228
+ "w e",
1229
+ "r i",
1230
+ "h a",
1231
+ "wi th",
1232
+ "gh t",
1233
+ "ou t",
1234
+ "i m",
1235
+ "i on",
1236
+ "al l",
1237
+ "a b",
1238
+ "on e",
1239
+ "n e",
1240
+ "g e",
1241
+ "ou ld",
1242
+ "t er",
1243
+ "m o",
1244
+ "h ad",
1245
+ "c e",
1246
+ "s he",
1247
+ "g o",
1248
+ "s h",
1249
+ "u r",
1250
+ "a m",
1251
+ "s o",
1252
+ "p e",
1253
+ "m y",
1254
+ "d e",
1255
+ "a re",
1256
+ "b ut",
1257
+ "om e",
1258
+ "f r",
1259
+ "the r",
1260
+ "f e",
1261
+ "s u",
1262
+ "d o",
1263
+ "c on",
1264
+ "t e",
1265
+ "a in",
1266
+ "er e",
1267
+ "p o",
1268
+ "i f",
1269
+ "the y",
1270
+ "u s",
1271
+ "a g",
1272
+ "t r",
1273
+ "n ow",
1274
+ "ou n",
1275
+ "th is",
1276
+ "ha ve",
1277
+ "no t",
1278
+ "s a",
1279
+ "i l",
1280
+ "u p",
1281
+ "th ing",
1282
+ "fr om",
1283
+ "a p",
1284
+ "h im",
1285
+ "ac k",
1286
+ "at ion",
1287
+ "an t",
1288
+ "ou r",
1289
+ "o p",
1290
+ "li ke",
1291
+ "u st",
1292
+ "es s",
1293
+ "b o",
1294
+ "o k",
1295
+ "u l",
1296
+ "in d",
1297
+ "e x",
1298
+ "c om",
1299
+ "s ome",
1300
+ "the re",
1301
+ "er s",
1302
+ "c o",
1303
+ "re s",
1304
+ "m an",
1305
+ "ar d",
1306
+ "p l",
1307
+ "w or",
1308
+ "w ay",
1309
+ "ti on",
1310
+ "f o",
1311
+ "c a",
1312
+ "w ere",
1313
+ "b y",
1314
+ "at e",
1315
+ "p ro",
1316
+ "t ed",
1317
+ "oun d",
1318
+ "ow n",
1319
+ "w ould",
1320
+ "t s",
1321
+ "wh at",
1322
+ "q u",
1323
+ "al ly",
1324
+ "i ght",
1325
+ "c k",
1326
+ "g r",
1327
+ "wh en",
1328
+ "v en",
1329
+ "c an",
1330
+ "ou gh",
1331
+ "in e",
1332
+ "en d",
1333
+ "p er",
1334
+ "ou s",
1335
+ "o d",
1336
+ "id e",
1337
+ "k now",
1338
+ "t y",
1339
+ "ver y",
1340
+ "s i",
1341
+ "a k",
1342
+ "wh o",
1343
+ "ab out",
1344
+ "i ll",
1345
+ "the m",
1346
+ "es t",
1347
+ "re d",
1348
+ "y e",
1349
+ "c ould",
1350
+ "on g",
1351
+ "you r",
1352
+ "the ir",
1353
+ "e m",
1354
+ "j ust",
1355
+ "o ther",
1356
+ "in to",
1357
+ "an y",
1358
+ "wh i",
1359
+ "u m",
1360
+ "t w",
1361
+ "as t",
1362
+ "d er",
1363
+ "d id",
1364
+ "i e",
1365
+ "be en",
1366
+ "ac e",
1367
+ "in k",
1368
+ "it y",
1369
+ "b ack",
1370
+ "t ing",
1371
+ "b r",
1372
+ "mo re",
1373
+ "a ke",
1374
+ "p p",
1375
+ "the n",
1376
+ "s p",
1377
+ "e l",
1378
+ "u se",
1379
+ "b l",
1380
+ "sa id",
1381
+ "o ver",
1382
+ "ge t",
1383
+ "ɑ ː",
1384
+ "i ː",
1385
+ "u ː",
1386
+ "ɜ ː",
1387
+ "ɔ ː",
1388
+ "o ː",
1389
+ "e ɪ",
1390
+ "o ʊ",
1391
+ "a ɪ",
1392
+ "a ʊ",
1393
+ "ɔ ɪ",
1394
+ "d ʒ",
1395
+ "t ʃ",
1396
+ "ɪ ŋ",
1397
+ "ᵻ d",
1398
+ "ˈ iː",
1399
+ "ˌ iː",
1400
+ "ˈ ɪ",
1401
+ "ˌ ɪ",
1402
+ "ˈ eɪ",
1403
+ "ˌ eɪ",
1404
+ "ˈ ɛ",
1405
+ "ˌ ɛ",
1406
+ "ˈ æ",
1407
+ "ˌ æ",
1408
+ "ˈ ɑː",
1409
+ "ˌ ɑː",
1410
+ "ˈ ɔː",
1411
+ "ˌ ɔː",
1412
+ "oː ɹ",
1413
+ "ˈ oːɹ",
1414
+ "ˌ oːɹ",
1415
+ "ˈ oʊ",
1416
+ "ˌ oʊ",
1417
+ "ˈ ʊ",
1418
+ "ˌ ʊ",
1419
+ "ˈ uː",
1420
+ "ˌ uː",
1421
+ "ˈ ɜː",
1422
+ "ˌ ɜː",
1423
+ "ˈ ʌ",
1424
+ "ˌ ʌ",
1425
+ "ˈ aɪ",
1426
+ "ˌ aɪ",
1427
+ "ˈ aʊ",
1428
+ "ˌ aʊ",
1429
+ "ˈ ɔɪ",
1430
+ "ˌ ɔɪ",
1431
+ "ˈ ɚ",
1432
+ "ˌ ɐ"
1433
+ ]
1434
+ }
1435
+ }
en/onnx/chatterbox-onnx/tokenizer_config.json ADDED
@@ -0,0 +1,2061 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 131072,
2060
+ "tokenizer_class": "PreTrainedTokenizerFast"
2061
+ }
en/onnx/chatterbox-onnx/vc_tokenizer_weights.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1ded72ff76cd97a688fad7506098fe247806b9922d0d8a0923f2d827532de6
3
+ size 495000154
en/onnx/chatterbox_ONNX/.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ llama3.onnx.data filter=lfs diff=lfs merge=lfs -text
37
+ llama3.data filter=lfs diff=lfs merge=lfs -text
en/onnx/chatterbox_ONNX/conditional_decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba02c957ad02eacc409f1fd85b9f6815f3a15b99385a8e94e101645afa390f4
3
+ size 294921432
en/onnx/chatterbox_ONNX/flow_inference.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0052bc19f6d844f0f793a8010433f1df829d350b720b04700b86a52edccecf
3
+ size 185917375
en/onnx/chatterbox_ONNX/llama3.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a763b2501b0022b6405ddbd3fd1a0ee36c4b58731199e035d55efdb3424bad
3
+ size 2080645120
en/onnx/chatterbox_ONNX/llama3.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9cc8435d74a378709fb44057d1d8a4bfba1d6ce334668d5fd8cfb8e0a14684
3
+ size 222296
en/onnx/chatterbox_ONNX/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/vladislavbro/chatterbox_ONNX
en/onnx/chatterbox_ONNX/speech_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2881465fcc4c4dcb92944d7d89da7262629240a7589090a01fcd016f23254f
3
+ size 79677508
en/onnx/chatterbox_ONNX/tokenizer.json ADDED
@@ -0,0 +1,1435 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "special": true,
9
+ "content": "[STOP]",
10
+ "single_word": false,
11
+ "lstrip": false,
12
+ "rstrip": false,
13
+ "normalized": false
14
+ },
15
+ {
16
+ "id": 1,
17
+ "special": true,
18
+ "content": "[UNK]",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false
23
+ },
24
+ {
25
+ "id": 2,
26
+ "special": true,
27
+ "content": "[SPACE]",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false
32
+ },
33
+ {
34
+ "id": 255,
35
+ "special": true,
36
+ "content": "[START]",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false
41
+ },
42
+ {
43
+ "id": 604,
44
+ "content": "[UH]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 605,
53
+ "content": "[UM]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 606,
62
+ "content": "[giggle]",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 607,
71
+ "content": "[laughter]",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 608,
80
+ "content": "[guffaw]",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 609,
89
+ "content": "[inhale]",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 610,
98
+ "content": "[exhale]",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 611,
107
+ "content": "[sigh]",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 612,
116
+ "content": "[cry]",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 613,
125
+ "content": "[bark]",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 614,
134
+ "content": "[howl]",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 615,
143
+ "content": "[meow]",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 616,
152
+ "content": "[singing]",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 617,
161
+ "content": "[music]",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 618,
170
+ "content": "[whistle]",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 619,
179
+ "content": "[humming]",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 620,
188
+ "content": "[gasp]",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 621,
197
+ "content": "[groan]",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 622,
206
+ "content": "[whisper]",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 623,
215
+ "content": "[mumble]",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 624,
224
+ "content": "[sniff]",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 625,
233
+ "content": "[sneeze]",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 626,
242
+ "content": "[cough]",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 627,
251
+ "content": "[snore]",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 628,
260
+ "content": "[chew]",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 629,
269
+ "content": "[sip]",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 630,
278
+ "content": "[clear_throat]",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 631,
287
+ "content": "[kiss]",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 632,
296
+ "content": "[shhh]",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 633,
305
+ "content": "[gibberish]",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 634,
314
+ "content": "[fr]",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 635,
323
+ "content": "[es]",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 636,
332
+ "content": "[de]",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 637,
341
+ "content": "[it]",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 638,
350
+ "content": "[ipa]",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 639,
359
+ "content": "[end_of_label]",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 695,
368
+ "content": "[PLACEHOLDER55]",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 696,
377
+ "content": "[PLACEHOLDER56]",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 697,
386
+ "content": "[PLACEHOLDER57]",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 698,
395
+ "content": "[PLACEHOLDER58]",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 699,
404
+ "content": "[PLACEHOLDER59]",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 700,
413
+ "content": "[PLACEHOLDER60]",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 701,
422
+ "content": "[PLACEHOLDER61]",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 702,
431
+ "content": "[PLACEHOLDER62]",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 703,
440
+ "content": "[PLACEHOLDER63]",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ }
447
+ ],
448
+ "normalizer": null,
449
+ "pre_tokenizer": {
450
+ "type": "Whitespace"
451
+ },
452
+ "post_processor": null,
453
+ "decoder": null,
454
+ "model": {
455
+ "type": "BPE",
456
+ "dropout": null,
457
+ "unk_token": "[UNK]",
458
+ "continuing_subword_prefix": null,
459
+ "end_of_word_suffix": null,
460
+ "fuse_unk": false,
461
+ "vocab": {
462
+ "[STOP]": 0,
463
+ "[UNK]": 1,
464
+ "[SPACE]": 2,
465
+ "!": 3,
466
+ "'": 4,
467
+ "(": 5,
468
+ ")": 6,
469
+ ",": 7,
470
+ "-": 8,
471
+ ".": 9,
472
+ "/": 10,
473
+ ":": 11,
474
+ ";": 12,
475
+ "?": 13,
476
+ "a": 14,
477
+ "b": 15,
478
+ "c": 16,
479
+ "d": 17,
480
+ "e": 18,
481
+ "f": 19,
482
+ "g": 20,
483
+ "h": 21,
484
+ "i": 22,
485
+ "j": 23,
486
+ "k": 24,
487
+ "l": 25,
488
+ "m": 26,
489
+ "n": 27,
490
+ "o": 28,
491
+ "p": 29,
492
+ "q": 30,
493
+ "r": 31,
494
+ "s": 32,
495
+ "t": 33,
496
+ "u": 34,
497
+ "v": 35,
498
+ "w": 36,
499
+ "x": 37,
500
+ "y": 38,
501
+ "z": 39,
502
+ "th": 40,
503
+ "in": 41,
504
+ "the": 42,
505
+ "an": 43,
506
+ "er": 44,
507
+ "ou": 45,
508
+ "re": 46,
509
+ "on": 47,
510
+ "at": 48,
511
+ "ed": 49,
512
+ "en": 50,
513
+ "to": 51,
514
+ "ing": 52,
515
+ "and": 53,
516
+ "is": 54,
517
+ "as": 55,
518
+ "al": 56,
519
+ "or": 57,
520
+ "of": 58,
521
+ "ar": 59,
522
+ "it": 60,
523
+ "es": 61,
524
+ "he": 62,
525
+ "st": 63,
526
+ "le": 64,
527
+ "om": 65,
528
+ "se": 66,
529
+ "be": 67,
530
+ "ad": 68,
531
+ "ow": 69,
532
+ "ly": 70,
533
+ "ch": 71,
534
+ "wh": 72,
535
+ "that": 73,
536
+ "you": 74,
537
+ "li": 75,
538
+ "ve": 76,
539
+ "ac": 77,
540
+ "ti": 78,
541
+ "ld": 79,
542
+ "me": 80,
543
+ "was": 81,
544
+ "gh": 82,
545
+ "id": 83,
546
+ "ll": 84,
547
+ "wi": 85,
548
+ "ent": 86,
549
+ "for": 87,
550
+ "ay": 88,
551
+ "ro": 89,
552
+ "ver": 90,
553
+ "ic": 91,
554
+ "her": 92,
555
+ "ke": 93,
556
+ "his": 94,
557
+ "no": 95,
558
+ "ut": 96,
559
+ "un": 97,
560
+ "ir": 98,
561
+ "lo": 99,
562
+ "we": 100,
563
+ "ri": 101,
564
+ "ha": 102,
565
+ "with": 103,
566
+ "ght": 104,
567
+ "out": 105,
568
+ "im": 106,
569
+ "ion": 107,
570
+ "all": 108,
571
+ "ab": 109,
572
+ "one": 110,
573
+ "ne": 111,
574
+ "ge": 112,
575
+ "ould": 113,
576
+ "ter": 114,
577
+ "mo": 115,
578
+ "had": 116,
579
+ "ce": 117,
580
+ "she": 118,
581
+ "go": 119,
582
+ "sh": 120,
583
+ "ur": 121,
584
+ "am": 122,
585
+ "so": 123,
586
+ "pe": 124,
587
+ "my": 125,
588
+ "de": 126,
589
+ "are": 127,
590
+ "but": 128,
591
+ "ome": 129,
592
+ "fr": 130,
593
+ "ther": 131,
594
+ "fe": 132,
595
+ "su": 133,
596
+ "do": 134,
597
+ "con": 135,
598
+ "te": 136,
599
+ "ain": 137,
600
+ "ere": 138,
601
+ "po": 139,
602
+ "if": 140,
603
+ "they": 141,
604
+ "us": 142,
605
+ "ag": 143,
606
+ "tr": 144,
607
+ "now": 145,
608
+ "oun": 146,
609
+ "this": 147,
610
+ "have": 148,
611
+ "not": 149,
612
+ "sa": 150,
613
+ "il": 151,
614
+ "up": 152,
615
+ "thing": 153,
616
+ "from": 154,
617
+ "ap": 155,
618
+ "him": 156,
619
+ "ack": 157,
620
+ "ation": 158,
621
+ "ant": 159,
622
+ "our": 160,
623
+ "op": 161,
624
+ "like": 162,
625
+ "ust": 163,
626
+ "ess": 164,
627
+ "bo": 165,
628
+ "ok": 166,
629
+ "ul": 167,
630
+ "ind": 168,
631
+ "ex": 169,
632
+ "com": 170,
633
+ "some": 171,
634
+ "there": 172,
635
+ "ers": 173,
636
+ "co": 174,
637
+ "res": 175,
638
+ "man": 176,
639
+ "ard": 177,
640
+ "pl": 178,
641
+ "wor": 179,
642
+ "way": 180,
643
+ "tion": 181,
644
+ "fo": 182,
645
+ "ca": 183,
646
+ "were": 184,
647
+ "by": 185,
648
+ "ate": 186,
649
+ "pro": 187,
650
+ "ted": 188,
651
+ "ound": 189,
652
+ "own": 190,
653
+ "would": 191,
654
+ "ts": 192,
655
+ "what": 193,
656
+ "qu": 194,
657
+ "ally": 195,
658
+ "ight": 196,
659
+ "ck": 197,
660
+ "gr": 198,
661
+ "when": 199,
662
+ "ven": 200,
663
+ "can": 201,
664
+ "ough": 202,
665
+ "ine": 203,
666
+ "end": 204,
667
+ "per": 205,
668
+ "ous": 206,
669
+ "od": 207,
670
+ "ide": 208,
671
+ "know": 209,
672
+ "ty": 210,
673
+ "very": 211,
674
+ "si": 212,
675
+ "ak": 213,
676
+ "who": 214,
677
+ "about": 215,
678
+ "ill": 216,
679
+ "them": 217,
680
+ "est": 218,
681
+ "red": 219,
682
+ "ye": 220,
683
+ "could": 221,
684
+ "ong": 222,
685
+ "your": 223,
686
+ "their": 224,
687
+ "em": 225,
688
+ "just": 226,
689
+ "other": 227,
690
+ "into": 228,
691
+ "any": 229,
692
+ "whi": 230,
693
+ "um": 231,
694
+ "tw": 232,
695
+ "ast": 233,
696
+ "der": 234,
697
+ "did": 235,
698
+ "ie": 236,
699
+ "been": 237,
700
+ "ace": 238,
701
+ "ink": 239,
702
+ "ity": 240,
703
+ "back": 241,
704
+ "ting": 242,
705
+ "br": 243,
706
+ "more": 244,
707
+ "ake": 245,
708
+ "pp": 246,
709
+ "then": 247,
710
+ "sp": 248,
711
+ "el": 249,
712
+ "use": 250,
713
+ "bl": 251,
714
+ "said": 252,
715
+ "over": 253,
716
+ "get": 254,
717
+ "[START]": 255,
718
+ "\"": 256,
719
+ "#": 257,
720
+ "$": 258,
721
+ "%": 259,
722
+ "&": 260,
723
+ "*": 261,
724
+ "+": 262,
725
+ "0": 263,
726
+ "1": 264,
727
+ "2": 265,
728
+ "3": 266,
729
+ "4": 267,
730
+ "5": 268,
731
+ "6": 269,
732
+ "7": 270,
733
+ "8": 271,
734
+ "9": 272,
735
+ "<": 273,
736
+ "=": 274,
737
+ ">": 275,
738
+ "@": 276,
739
+ "A": 277,
740
+ "B": 278,
741
+ "C": 279,
742
+ "D": 280,
743
+ "E": 281,
744
+ "F": 282,
745
+ "G": 283,
746
+ "H": 284,
747
+ "I": 285,
748
+ "J": 286,
749
+ "K": 287,
750
+ "L": 288,
751
+ "M": 289,
752
+ "N": 290,
753
+ "O": 291,
754
+ "P": 292,
755
+ "Q": 293,
756
+ "R": 294,
757
+ "S": 295,
758
+ "T": 296,
759
+ "U": 297,
760
+ "V": 298,
761
+ "W": 299,
762
+ "X": 300,
763
+ "Y": 301,
764
+ "Z": 302,
765
+ "[": 303,
766
+ "\\": 304,
767
+ "]": 305,
768
+ "^": 306,
769
+ "_": 307,
770
+ "`": 308,
771
+ "{": 309,
772
+ "|": 310,
773
+ "}": 311,
774
+ "~": 312,
775
+ "‐": 313,
776
+ "‑": 314,
777
+ "‒": 315,
778
+ "–": 316,
779
+ "—": 317,
780
+ "―": 318,
781
+ "‖": 319,
782
+ "‗": 320,
783
+ "‘": 321,
784
+ "’": 322,
785
+ "‚": 323,
786
+ "‛": 324,
787
+ "“": 325,
788
+ "”": 326,
789
+ "„": 327,
790
+ "‟": 328,
791
+ " ": 329,
792
+ "¡": 330,
793
+ "¢": 331,
794
+ "£": 332,
795
+ "¤": 333,
796
+ "¥": 334,
797
+ "¦": 335,
798
+ "§": 336,
799
+ "¨": 337,
800
+ "©": 338,
801
+ "ª": 339,
802
+ "«": 340,
803
+ "¬": 341,
804
+ "­": 342,
805
+ "®": 343,
806
+ "¯": 344,
807
+ "°": 345,
808
+ "±": 346,
809
+ "²": 347,
810
+ "³": 348,
811
+ "´": 349,
812
+ "µ": 350,
813
+ "¶": 351,
814
+ "·": 352,
815
+ "¸": 353,
816
+ "¹": 354,
817
+ "º": 355,
818
+ "»": 356,
819
+ "¼": 357,
820
+ "½": 358,
821
+ "¾": 359,
822
+ "¿": 360,
823
+ "À": 361,
824
+ "Á": 362,
825
+ "Â": 363,
826
+ "Ã": 364,
827
+ "Ä": 365,
828
+ "Å": 366,
829
+ "Æ": 367,
830
+ "Ç": 368,
831
+ "È": 369,
832
+ "É": 370,
833
+ "Ê": 371,
834
+ "Ë": 372,
835
+ "Ì": 373,
836
+ "Í": 374,
837
+ "Î": 375,
838
+ "Ï": 376,
839
+ "Ð": 377,
840
+ "Ñ": 378,
841
+ "Ò": 379,
842
+ "Ó": 380,
843
+ "Ô": 381,
844
+ "Õ": 382,
845
+ "Ö": 383,
846
+ "×": 384,
847
+ "Ø": 385,
848
+ "Ù": 386,
849
+ "Ú": 387,
850
+ "Û": 388,
851
+ "Ü": 389,
852
+ "Ý": 390,
853
+ "Þ": 391,
854
+ "ß": 392,
855
+ "à": 393,
856
+ "á": 394,
857
+ "â": 395,
858
+ "ã": 396,
859
+ "ä": 397,
860
+ "å": 398,
861
+ "æ": 399,
862
+ "ç": 400,
863
+ "è": 401,
864
+ "é": 402,
865
+ "ê": 403,
866
+ "ë": 404,
867
+ "ì": 405,
868
+ "í": 406,
869
+ "î": 407,
870
+ "ï": 408,
871
+ "ð": 409,
872
+ "ñ": 410,
873
+ "ò": 411,
874
+ "ó": 412,
875
+ "ô": 413,
876
+ "õ": 414,
877
+ "ö": 415,
878
+ "÷": 416,
879
+ "ø": 417,
880
+ "ù": 418,
881
+ "ú": 419,
882
+ "û": 420,
883
+ "ü": 421,
884
+ "ý": 422,
885
+ "þ": 423,
886
+ "ÿ": 424,
887
+ "ɐ": 425,
888
+ "ɑ": 426,
889
+ "ɒ": 427,
890
+ "ɓ": 428,
891
+ "ɔ": 429,
892
+ "ɕ": 430,
893
+ "ɖ": 431,
894
+ "ɗ": 432,
895
+ "ɘ": 433,
896
+ "ə": 434,
897
+ "ɚ": 435,
898
+ "ɛ": 436,
899
+ "ɜ": 437,
900
+ "ɝ": 438,
901
+ "ɞ": 439,
902
+ "ɟ": 440,
903
+ "ɠ": 441,
904
+ "ɡ": 442,
905
+ "ɢ": 443,
906
+ "ɣ": 444,
907
+ "ɤ": 445,
908
+ "ɥ": 446,
909
+ "ɦ": 447,
910
+ "ɧ": 448,
911
+ "ɨ": 449,
912
+ "ɩ": 450,
913
+ "ɪ": 451,
914
+ "ɫ": 452,
915
+ "ɬ": 453,
916
+ "ɭ": 454,
917
+ "ɮ": 455,
918
+ "ɯ": 456,
919
+ "ɰ": 457,
920
+ "ɱ": 458,
921
+ "ɲ": 459,
922
+ "ɳ": 460,
923
+ "ɴ": 461,
924
+ "ɵ": 462,
925
+ "ɶ": 463,
926
+ "ɷ": 464,
927
+ "ɸ": 465,
928
+ "ɹ": 466,
929
+ "ɺ": 467,
930
+ "ɻ": 468,
931
+ "ɼ": 469,
932
+ "ɽ": 470,
933
+ "ɾ": 471,
934
+ "ɿ": 472,
935
+ "ʀ": 473,
936
+ "ʁ": 474,
937
+ "ʂ": 475,
938
+ "ʃ": 476,
939
+ "ʄ": 477,
940
+ "ʅ": 478,
941
+ "ʆ": 479,
942
+ "ʇ": 480,
943
+ "ʈ": 481,
944
+ "ʉ": 482,
945
+ "ʊ": 483,
946
+ "ʋ": 484,
947
+ "ʌ": 485,
948
+ "ʍ": 486,
949
+ "ʎ": 487,
950
+ "ʏ": 488,
951
+ "ʐ": 489,
952
+ "ʑ": 490,
953
+ "ʒ": 491,
954
+ "ʓ": 492,
955
+ "ʔ": 493,
956
+ "ʕ": 494,
957
+ "ʖ": 495,
958
+ "ʗ": 496,
959
+ "ʘ": 497,
960
+ "ʙ": 498,
961
+ "ʚ": 499,
962
+ "ʛ": 500,
963
+ "ʜ": 501,
964
+ "ʝ": 502,
965
+ "ʞ": 503,
966
+ "ʟ": 504,
967
+ "ʠ": 505,
968
+ "ʡ": 506,
969
+ "ʢ": 507,
970
+ "ʣ": 508,
971
+ "ʤ": 509,
972
+ "ʥ": 510,
973
+ "ʦ": 511,
974
+ "ʧ": 512,
975
+ "ʨ": 513,
976
+ "ʩ": 514,
977
+ "ʪ": 515,
978
+ "ʫ": 516,
979
+ "ʬ": 517,
980
+ "ʭ": 518,
981
+ "ʮ": 519,
982
+ "ʯ": 520,
983
+ "ʰ": 521,
984
+ "ʱ": 522,
985
+ "ʲ": 523,
986
+ "ʳ": 524,
987
+ "ʴ": 525,
988
+ "ʵ": 526,
989
+ "ʶ": 527,
990
+ "ʷ": 528,
991
+ "ʸ": 529,
992
+ "ʹ": 530,
993
+ "ʺ": 531,
994
+ "ʻ": 532,
995
+ "ʼ": 533,
996
+ "ʽ": 534,
997
+ "ʾ": 535,
998
+ "ʿ": 536,
999
+ "ˀ": 537,
1000
+ "ˁ": 538,
1001
+ "˂": 539,
1002
+ "˃": 540,
1003
+ "˄": 541,
1004
+ "˅": 542,
1005
+ "ˆ": 543,
1006
+ "ˇ": 544,
1007
+ "ˈ": 545,
1008
+ "ˉ": 546,
1009
+ "ˊ": 547,
1010
+ "ˋ": 548,
1011
+ "ˌ": 549,
1012
+ "ˍ": 550,
1013
+ "ˎ": 551,
1014
+ "ˏ": 552,
1015
+ "ː": 553,
1016
+ "ˑ": 554,
1017
+ "˒": 555,
1018
+ "˓": 556,
1019
+ "˔": 557,
1020
+ "˕": 558,
1021
+ "˖": 559,
1022
+ "˗": 560,
1023
+ "˘": 561,
1024
+ "˙": 562,
1025
+ "˚": 563,
1026
+ "˛": 564,
1027
+ "˜": 565,
1028
+ "˝": 566,
1029
+ "˞": 567,
1030
+ "˟": 568,
1031
+ "ˠ": 569,
1032
+ "ˡ": 570,
1033
+ "ˢ": 571,
1034
+ "ˣ": 572,
1035
+ "ˤ": 573,
1036
+ "˥": 574,
1037
+ "˦": 575,
1038
+ "˧": 576,
1039
+ "˨": 577,
1040
+ "˩": 578,
1041
+ "˪": 579,
1042
+ "˫": 580,
1043
+ "ˬ": 581,
1044
+ "˭": 582,
1045
+ "ˮ": 583,
1046
+ "˯": 584,
1047
+ "˰": 585,
1048
+ "˱": 586,
1049
+ "˲": 587,
1050
+ "˳": 588,
1051
+ "˴": 589,
1052
+ "˵": 590,
1053
+ "˶": 591,
1054
+ "˷": 592,
1055
+ "˸": 593,
1056
+ "˹": 594,
1057
+ "˺": 595,
1058
+ "˻": 596,
1059
+ "˼": 597,
1060
+ "˽": 598,
1061
+ "˾": 599,
1062
+ "˿": 600,
1063
+ "ā": 601,
1064
+ "ō": 602,
1065
+ "…": 603,
1066
+ "[UH]": 604,
1067
+ "[UM]": 605,
1068
+ "[giggle]": 606,
1069
+ "[laughter]": 607,
1070
+ "[guffaw]": 608,
1071
+ "[inhale]": 609,
1072
+ "[exhale]": 610,
1073
+ "[sigh]": 611,
1074
+ "[cry]": 612,
1075
+ "[bark]": 613,
1076
+ "[howl]": 614,
1077
+ "[meow]": 615,
1078
+ "[singing]": 616,
1079
+ "[music]": 617,
1080
+ "[whistle]": 618,
1081
+ "[humming]": 619,
1082
+ "[gasp]": 620,
1083
+ "[groan]": 621,
1084
+ "[whisper]": 622,
1085
+ "[mumble]": 623,
1086
+ "[sniff]": 624,
1087
+ "[sneeze]": 625,
1088
+ "[cough]": 626,
1089
+ "[snore]": 627,
1090
+ "[chew]": 628,
1091
+ "[sip]": 629,
1092
+ "[clear_throat]": 630,
1093
+ "[kiss]": 631,
1094
+ "[shhh]": 632,
1095
+ "[gibberish]": 633,
1096
+ "[fr]": 634,
1097
+ "[es]": 635,
1098
+ "[de]": 636,
1099
+ "[it]": 637,
1100
+ "[ipa]": 638,
1101
+ "[end_of_label]": 639,
1102
+ "ŋ": 640,
1103
+ "ᵻ": 641,
1104
+ "θ": 642,
1105
+ "̩": 643,
1106
+ "\u0303": 644,
1107
+ "ɑː": 645,
1108
+ "iː": 646,
1109
+ "uː": 647,
1110
+ "ɜː": 648,
1111
+ "ɔː": 649,
1112
+ "oː": 650,
1113
+ "eɪ": 651,
1114
+ "oʊ": 652,
1115
+ "aɪ": 653,
1116
+ "aʊ": 654,
1117
+ "ɔɪ": 655,
1118
+ "dʒ": 656,
1119
+ "tʃ": 657,
1120
+ "ɪŋ": 658,
1121
+ "ᵻd": 659,
1122
+ "ˈiː": 660,
1123
+ "ˌiː": 661,
1124
+ "ˈɪ": 662,
1125
+ "ˌɪ": 663,
1126
+ "ˈeɪ": 664,
1127
+ "ˌeɪ": 665,
1128
+ "ˈɛ": 666,
1129
+ "ˌɛ": 667,
1130
+ "ˈæ": 668,
1131
+ "ˌæ": 669,
1132
+ "ˈɑː": 670,
1133
+ "ˌɑː": 671,
1134
+ "ˈɔː": 672,
1135
+ "ˌɔː": 673,
1136
+ "oːɹ": 674,
1137
+ "ˈoːɹ": 675,
1138
+ "ˌoːɹ": 676,
1139
+ "ˈoʊ": 677,
1140
+ "ˌoʊ": 678,
1141
+ "ˈʊ": 679,
1142
+ "ˌʊ": 680,
1143
+ "ˈuː": 681,
1144
+ "ˌuː": 682,
1145
+ "ˈɜː": 683,
1146
+ "ˌɜː": 684,
1147
+ "ˈʌ": 685,
1148
+ "ˌʌ": 686,
1149
+ "ˈaɪ": 687,
1150
+ "ˌaɪ": 688,
1151
+ "ˈaʊ": 689,
1152
+ "ˌaʊ": 690,
1153
+ "ˈɔɪ": 691,
1154
+ "ˌɔɪ": 692,
1155
+ "ˈɚ": 693,
1156
+ "ˌɐ": 694,
1157
+ "[PLACEHOLDER55]": 695,
1158
+ "[PLACEHOLDER56]": 696,
1159
+ "[PLACEHOLDER57]": 697,
1160
+ "[PLACEHOLDER58]": 698,
1161
+ "[PLACEHOLDER59]": 699,
1162
+ "[PLACEHOLDER60]": 700,
1163
+ "[PLACEHOLDER61]": 701,
1164
+ "[PLACEHOLDER62]": 702,
1165
+ "[PLACEHOLDER63]": 703
1166
+ },
1167
+ "merges": [
1168
+ "t h",
1169
+ "i n",
1170
+ "th e",
1171
+ "a n",
1172
+ "e r",
1173
+ "o u",
1174
+ "r e",
1175
+ "o n",
1176
+ "a t",
1177
+ "e d",
1178
+ "e n",
1179
+ "t o",
1180
+ "in g",
1181
+ "an d",
1182
+ "i s",
1183
+ "a s",
1184
+ "a l",
1185
+ "o r",
1186
+ "o f",
1187
+ "a r",
1188
+ "i t",
1189
+ "e s",
1190
+ "h e",
1191
+ "s t",
1192
+ "l e",
1193
+ "o m",
1194
+ "s e",
1195
+ "b e",
1196
+ "a d",
1197
+ "o w",
1198
+ "l y",
1199
+ "c h",
1200
+ "w h",
1201
+ "th at",
1202
+ "y ou",
1203
+ "l i",
1204
+ "v e",
1205
+ "a c",
1206
+ "t i",
1207
+ "l d",
1208
+ "m e",
1209
+ "w as",
1210
+ "g h",
1211
+ "i d",
1212
+ "l l",
1213
+ "w i",
1214
+ "en t",
1215
+ "f or",
1216
+ "a y",
1217
+ "r o",
1218
+ "v er",
1219
+ "i c",
1220
+ "h er",
1221
+ "k e",
1222
+ "h is",
1223
+ "n o",
1224
+ "u t",
1225
+ "u n",
1226
+ "i r",
1227
+ "l o",
1228
+ "w e",
1229
+ "r i",
1230
+ "h a",
1231
+ "wi th",
1232
+ "gh t",
1233
+ "ou t",
1234
+ "i m",
1235
+ "i on",
1236
+ "al l",
1237
+ "a b",
1238
+ "on e",
1239
+ "n e",
1240
+ "g e",
1241
+ "ou ld",
1242
+ "t er",
1243
+ "m o",
1244
+ "h ad",
1245
+ "c e",
1246
+ "s he",
1247
+ "g o",
1248
+ "s h",
1249
+ "u r",
1250
+ "a m",
1251
+ "s o",
1252
+ "p e",
1253
+ "m y",
1254
+ "d e",
1255
+ "a re",
1256
+ "b ut",
1257
+ "om e",
1258
+ "f r",
1259
+ "the r",
1260
+ "f e",
1261
+ "s u",
1262
+ "d o",
1263
+ "c on",
1264
+ "t e",
1265
+ "a in",
1266
+ "er e",
1267
+ "p o",
1268
+ "i f",
1269
+ "the y",
1270
+ "u s",
1271
+ "a g",
1272
+ "t r",
1273
+ "n ow",
1274
+ "ou n",
1275
+ "th is",
1276
+ "ha ve",
1277
+ "no t",
1278
+ "s a",
1279
+ "i l",
1280
+ "u p",
1281
+ "th ing",
1282
+ "fr om",
1283
+ "a p",
1284
+ "h im",
1285
+ "ac k",
1286
+ "at ion",
1287
+ "an t",
1288
+ "ou r",
1289
+ "o p",
1290
+ "li ke",
1291
+ "u st",
1292
+ "es s",
1293
+ "b o",
1294
+ "o k",
1295
+ "u l",
1296
+ "in d",
1297
+ "e x",
1298
+ "c om",
1299
+ "s ome",
1300
+ "the re",
1301
+ "er s",
1302
+ "c o",
1303
+ "re s",
1304
+ "m an",
1305
+ "ar d",
1306
+ "p l",
1307
+ "w or",
1308
+ "w ay",
1309
+ "ti on",
1310
+ "f o",
1311
+ "c a",
1312
+ "w ere",
1313
+ "b y",
1314
+ "at e",
1315
+ "p ro",
1316
+ "t ed",
1317
+ "oun d",
1318
+ "ow n",
1319
+ "w ould",
1320
+ "t s",
1321
+ "wh at",
1322
+ "q u",
1323
+ "al ly",
1324
+ "i ght",
1325
+ "c k",
1326
+ "g r",
1327
+ "wh en",
1328
+ "v en",
1329
+ "c an",
1330
+ "ou gh",
1331
+ "in e",
1332
+ "en d",
1333
+ "p er",
1334
+ "ou s",
1335
+ "o d",
1336
+ "id e",
1337
+ "k now",
1338
+ "t y",
1339
+ "ver y",
1340
+ "s i",
1341
+ "a k",
1342
+ "wh o",
1343
+ "ab out",
1344
+ "i ll",
1345
+ "the m",
1346
+ "es t",
1347
+ "re d",
1348
+ "y e",
1349
+ "c ould",
1350
+ "on g",
1351
+ "you r",
1352
+ "the ir",
1353
+ "e m",
1354
+ "j ust",
1355
+ "o ther",
1356
+ "in to",
1357
+ "an y",
1358
+ "wh i",
1359
+ "u m",
1360
+ "t w",
1361
+ "as t",
1362
+ "d er",
1363
+ "d id",
1364
+ "i e",
1365
+ "be en",
1366
+ "ac e",
1367
+ "in k",
1368
+ "it y",
1369
+ "b ack",
1370
+ "t ing",
1371
+ "b r",
1372
+ "mo re",
1373
+ "a ke",
1374
+ "p p",
1375
+ "the n",
1376
+ "s p",
1377
+ "e l",
1378
+ "u se",
1379
+ "b l",
1380
+ "sa id",
1381
+ "o ver",
1382
+ "ge t",
1383
+ "ɑ ː",
1384
+ "i ː",
1385
+ "u ː",
1386
+ "ɜ ː",
1387
+ "ɔ ː",
1388
+ "o ː",
1389
+ "e ɪ",
1390
+ "o ʊ",
1391
+ "a ɪ",
1392
+ "a ʊ",
1393
+ "ɔ ɪ",
1394
+ "d ʒ",
1395
+ "t ʃ",
1396
+ "ɪ ŋ",
1397
+ "ᵻ d",
1398
+ "ˈ iː",
1399
+ "ˌ iː",
1400
+ "ˈ ɪ",
1401
+ "ˌ ɪ",
1402
+ "ˈ eɪ",
1403
+ "ˌ eɪ",
1404
+ "ˈ ɛ",
1405
+ "ˌ ɛ",
1406
+ "ˈ æ",
1407
+ "ˌ æ",
1408
+ "ˈ ɑː",
1409
+ "ˌ ɑː",
1410
+ "ˈ ɔː",
1411
+ "ˌ ɔː",
1412
+ "oː ɹ",
1413
+ "ˈ oːɹ",
1414
+ "ˌ oːɹ",
1415
+ "ˈ oʊ",
1416
+ "ˌ oʊ",
1417
+ "ˈ ʊ",
1418
+ "ˌ ʊ",
1419
+ "ˈ uː",
1420
+ "ˌ uː",
1421
+ "ˈ ɜː",
1422
+ "ˌ ɜː",
1423
+ "ˈ ʌ",
1424
+ "ˌ ʌ",
1425
+ "ˈ aɪ",
1426
+ "ˌ aɪ",
1427
+ "ˈ aʊ",
1428
+ "ˌ aʊ",
1429
+ "ˈ ɔɪ",
1430
+ "ˌ ɔɪ",
1431
+ "ˈ ɚ",
1432
+ "ˌ ɐ"
1433
+ ]
1434
+ }
1435
+ }
en/onnx/chatterbox_ONNX/tokenizer_config.json ADDED
@@ -0,0 +1,2061 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 131072,
2060
+ "tokenizer_class": "PreTrainedTokenizerFast"
2061
+ }
multi/expanded_chatterbox_model/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
multi/expanded_chatterbox_model/conds.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6552d70568833628ba019c6b03459e77fe71ca197d5c560cef9411bee9d87f4e
3
+ size 107374
multi/expanded_chatterbox_model/s3gen.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b78103c654207393955e4900aac14a12de8ef25f4b09424f1ef91941f161d4e
3
+ size 1056484620
multi/expanded_chatterbox_model/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/IIEleven11/expanded_chatterbox_model
multi/expanded_chatterbox_model/t3_cfg.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f7c3b0b2cf74ced0beeb1dcf295f41a03c9507bdde8108d17dd4471f8a8f39
3
+ size 2137731056
multi/expanded_chatterbox_model/tokenizer.json ADDED
@@ -0,0 +1,2458 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "special": true,
9
+ "content": "[STOP]",
10
+ "single_word": false,
11
+ "lstrip": false,
12
+ "rstrip": false,
13
+ "normalized": false
14
+ },
15
+ {
16
+ "id": 1,
17
+ "special": true,
18
+ "content": "[UNK]",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false
23
+ },
24
+ {
25
+ "id": 2,
26
+ "special": true,
27
+ "content": "[SPACE]",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false
32
+ },
33
+ {
34
+ "id": 255,
35
+ "special": true,
36
+ "content": "[START]",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false
41
+ },
42
+ {
43
+ "id": 604,
44
+ "content": "[UH]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 605,
53
+ "content": "[UM]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 606,
62
+ "content": "[giggle]",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 607,
71
+ "content": "[laughter]",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 608,
80
+ "content": "[guffaw]",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 609,
89
+ "content": "[inhale]",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 610,
98
+ "content": "[exhale]",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 611,
107
+ "content": "[sigh]",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 612,
116
+ "content": "[cry]",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 613,
125
+ "content": "[bark]",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 614,
134
+ "content": "[howl]",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 615,
143
+ "content": "[meow]",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 616,
152
+ "content": "[singing]",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 617,
161
+ "content": "[music]",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 618,
170
+ "content": "[whistle]",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 619,
179
+ "content": "[humming]",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 620,
188
+ "content": "[gasp]",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 621,
197
+ "content": "[groan]",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 622,
206
+ "content": "[whisper]",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 623,
215
+ "content": "[mumble]",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 624,
224
+ "content": "[sniff]",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 625,
233
+ "content": "[sneeze]",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 626,
242
+ "content": "[cough]",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 627,
251
+ "content": "[snore]",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 628,
260
+ "content": "[chew]",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 629,
269
+ "content": "[sip]",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 630,
278
+ "content": "[clear_throat]",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 631,
287
+ "content": "[kiss]",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 632,
296
+ "content": "[shhh]",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 633,
305
+ "content": "[gibberish]",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 634,
314
+ "content": "[fr]",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 635,
323
+ "content": "[es]",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 636,
332
+ "content": "[de]",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 637,
341
+ "content": "[it]",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 638,
350
+ "content": "[ipa]",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 639,
359
+ "content": "[end_of_label]",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 695,
368
+ "content": "[PLACEHOLDER55]",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 696,
377
+ "content": "[PLACEHOLDER56]",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 697,
386
+ "content": "[PLACEHOLDER57]",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 698,
395
+ "content": "[PLACEHOLDER58]",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 699,
404
+ "content": "[PLACEHOLDER59]",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 700,
413
+ "content": "[PLACEHOLDER60]",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 701,
422
+ "content": "[PLACEHOLDER61]",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 702,
431
+ "content": "[PLACEHOLDER62]",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 703,
440
+ "content": "[PLACEHOLDER63]",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 704,
449
+ "content": "<c_click>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 705,
458
+ "content": "<x_click>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 706,
467
+ "content": "<q_click>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 707,
476
+ "content": "[xh]",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ }
483
+ ],
484
+ "normalizer": null,
485
+ "pre_tokenizer": {
486
+ "type": "Whitespace"
487
+ },
488
+ "post_processor": null,
489
+ "decoder": null,
490
+ "model": {
491
+ "type": "BPE",
492
+ "dropout": null,
493
+ "unk_token": "[UNK]",
494
+ "continuing_subword_prefix": null,
495
+ "end_of_word_suffix": null,
496
+ "fuse_unk": false,
497
+ "vocab": {
498
+ "[STOP]": 0,
499
+ "[UNK]": 1,
500
+ "[SPACE]": 2,
501
+ "!": 3,
502
+ "'": 4,
503
+ "(": 5,
504
+ ")": 6,
505
+ ",": 7,
506
+ "-": 8,
507
+ ".": 9,
508
+ "/": 10,
509
+ ":": 11,
510
+ ";": 12,
511
+ "?": 13,
512
+ "a": 14,
513
+ "b": 15,
514
+ "c": 16,
515
+ "d": 17,
516
+ "e": 18,
517
+ "f": 19,
518
+ "g": 20,
519
+ "h": 21,
520
+ "i": 22,
521
+ "j": 23,
522
+ "k": 24,
523
+ "l": 25,
524
+ "m": 26,
525
+ "n": 27,
526
+ "o": 28,
527
+ "p": 29,
528
+ "q": 30,
529
+ "r": 31,
530
+ "s": 32,
531
+ "t": 33,
532
+ "u": 34,
533
+ "v": 35,
534
+ "w": 36,
535
+ "x": 37,
536
+ "y": 38,
537
+ "z": 39,
538
+ "th": 40,
539
+ "in": 41,
540
+ "the": 42,
541
+ "an": 43,
542
+ "er": 44,
543
+ "ou": 45,
544
+ "re": 46,
545
+ "on": 47,
546
+ "at": 48,
547
+ "ed": 49,
548
+ "en": 50,
549
+ "to": 51,
550
+ "ing": 52,
551
+ "and": 53,
552
+ "is": 54,
553
+ "as": 55,
554
+ "al": 56,
555
+ "or": 57,
556
+ "of": 58,
557
+ "ar": 59,
558
+ "it": 60,
559
+ "es": 61,
560
+ "he": 62,
561
+ "st": 63,
562
+ "le": 64,
563
+ "om": 65,
564
+ "se": 66,
565
+ "be": 67,
566
+ "ad": 68,
567
+ "ow": 69,
568
+ "ly": 70,
569
+ "ch": 71,
570
+ "wh": 72,
571
+ "that": 73,
572
+ "you": 74,
573
+ "li": 75,
574
+ "ve": 76,
575
+ "ac": 77,
576
+ "ti": 78,
577
+ "ld": 79,
578
+ "me": 80,
579
+ "was": 81,
580
+ "gh": 82,
581
+ "id": 83,
582
+ "ll": 84,
583
+ "wi": 85,
584
+ "ent": 86,
585
+ "for": 87,
586
+ "ay": 88,
587
+ "ro": 89,
588
+ "ver": 90,
589
+ "ic": 91,
590
+ "her": 92,
591
+ "ke": 93,
592
+ "his": 94,
593
+ "no": 95,
594
+ "ut": 96,
595
+ "un": 97,
596
+ "ir": 98,
597
+ "lo": 99,
598
+ "we": 100,
599
+ "ri": 101,
600
+ "ha": 102,
601
+ "with": 103,
602
+ "ght": 104,
603
+ "out": 105,
604
+ "im": 106,
605
+ "ion": 107,
606
+ "all": 108,
607
+ "ab": 109,
608
+ "one": 110,
609
+ "ne": 111,
610
+ "ge": 112,
611
+ "ould": 113,
612
+ "ter": 114,
613
+ "mo": 115,
614
+ "had": 116,
615
+ "ce": 117,
616
+ "she": 118,
617
+ "go": 119,
618
+ "sh": 120,
619
+ "ur": 121,
620
+ "am": 122,
621
+ "so": 123,
622
+ "pe": 124,
623
+ "my": 125,
624
+ "de": 126,
625
+ "are": 127,
626
+ "but": 128,
627
+ "ome": 129,
628
+ "fr": 130,
629
+ "ther": 131,
630
+ "fe": 132,
631
+ "su": 133,
632
+ "do": 134,
633
+ "con": 135,
634
+ "te": 136,
635
+ "ain": 137,
636
+ "ere": 138,
637
+ "po": 139,
638
+ "if": 140,
639
+ "they": 141,
640
+ "us": 142,
641
+ "ag": 143,
642
+ "tr": 144,
643
+ "now": 145,
644
+ "oun": 146,
645
+ "this": 147,
646
+ "have": 148,
647
+ "not": 149,
648
+ "sa": 150,
649
+ "il": 151,
650
+ "up": 152,
651
+ "thing": 153,
652
+ "from": 154,
653
+ "ap": 155,
654
+ "him": 156,
655
+ "ack": 157,
656
+ "ation": 158,
657
+ "ant": 159,
658
+ "our": 160,
659
+ "op": 161,
660
+ "like": 162,
661
+ "ust": 163,
662
+ "ess": 164,
663
+ "bo": 165,
664
+ "ok": 166,
665
+ "ul": 167,
666
+ "ind": 168,
667
+ "ex": 169,
668
+ "com": 170,
669
+ "some": 171,
670
+ "there": 172,
671
+ "ers": 173,
672
+ "co": 174,
673
+ "res": 175,
674
+ "man": 176,
675
+ "ard": 177,
676
+ "pl": 178,
677
+ "wor": 179,
678
+ "way": 180,
679
+ "tion": 181,
680
+ "fo": 182,
681
+ "ca": 183,
682
+ "were": 184,
683
+ "by": 185,
684
+ "ate": 186,
685
+ "pro": 187,
686
+ "ted": 188,
687
+ "ound": 189,
688
+ "own": 190,
689
+ "would": 191,
690
+ "ts": 192,
691
+ "what": 193,
692
+ "qu": 194,
693
+ "ally": 195,
694
+ "ight": 196,
695
+ "ck": 197,
696
+ "gr": 198,
697
+ "when": 199,
698
+ "ven": 200,
699
+ "can": 201,
700
+ "ough": 202,
701
+ "ine": 203,
702
+ "end": 204,
703
+ "per": 205,
704
+ "ous": 206,
705
+ "od": 207,
706
+ "ide": 208,
707
+ "know": 209,
708
+ "ty": 210,
709
+ "very": 211,
710
+ "si": 212,
711
+ "ak": 213,
712
+ "who": 214,
713
+ "about": 215,
714
+ "ill": 216,
715
+ "them": 217,
716
+ "est": 218,
717
+ "red": 219,
718
+ "ye": 220,
719
+ "could": 221,
720
+ "ong": 222,
721
+ "your": 223,
722
+ "their": 224,
723
+ "em": 225,
724
+ "just": 226,
725
+ "other": 227,
726
+ "into": 228,
727
+ "any": 229,
728
+ "whi": 230,
729
+ "um": 231,
730
+ "tw": 232,
731
+ "ast": 233,
732
+ "der": 234,
733
+ "did": 235,
734
+ "ie": 236,
735
+ "been": 237,
736
+ "ace": 238,
737
+ "ink": 239,
738
+ "ity": 240,
739
+ "back": 241,
740
+ "ting": 242,
741
+ "br": 243,
742
+ "more": 244,
743
+ "ake": 245,
744
+ "pp": 246,
745
+ "then": 247,
746
+ "sp": 248,
747
+ "el": 249,
748
+ "use": 250,
749
+ "bl": 251,
750
+ "said": 252,
751
+ "over": 253,
752
+ "get": 254,
753
+ "[START]": 255,
754
+ "\"": 256,
755
+ "#": 257,
756
+ "$": 258,
757
+ "%": 259,
758
+ "&": 260,
759
+ "*": 261,
760
+ "+": 262,
761
+ "0": 263,
762
+ "1": 264,
763
+ "2": 265,
764
+ "3": 266,
765
+ "4": 267,
766
+ "5": 268,
767
+ "6": 269,
768
+ "7": 270,
769
+ "8": 271,
770
+ "9": 272,
771
+ "<": 273,
772
+ "=": 274,
773
+ ">": 275,
774
+ "@": 276,
775
+ "A": 277,
776
+ "B": 278,
777
+ "C": 279,
778
+ "D": 280,
779
+ "E": 281,
780
+ "F": 282,
781
+ "G": 283,
782
+ "H": 284,
783
+ "I": 285,
784
+ "J": 286,
785
+ "K": 287,
786
+ "L": 288,
787
+ "M": 289,
788
+ "N": 290,
789
+ "O": 291,
790
+ "P": 292,
791
+ "Q": 293,
792
+ "R": 294,
793
+ "S": 295,
794
+ "T": 296,
795
+ "U": 297,
796
+ "V": 298,
797
+ "W": 299,
798
+ "X": 300,
799
+ "Y": 301,
800
+ "Z": 302,
801
+ "[": 303,
802
+ "\\": 304,
803
+ "]": 305,
804
+ "^": 306,
805
+ "_": 307,
806
+ "`": 308,
807
+ "{": 309,
808
+ "|": 310,
809
+ "}": 311,
810
+ "~": 312,
811
+ "‐": 313,
812
+ "‑": 314,
813
+ "‒": 315,
814
+ "–": 316,
815
+ "—": 317,
816
+ "―": 318,
817
+ "‖": 319,
818
+ "‗": 320,
819
+ "‘": 321,
820
+ "’": 322,
821
+ "‚": 323,
822
+ "‛": 324,
823
+ "“": 325,
824
+ "”": 326,
825
+ "„": 327,
826
+ "‟": 328,
827
+ " ": 329,
828
+ "¡": 330,
829
+ "¢": 331,
830
+ "£": 332,
831
+ "¤": 333,
832
+ "¥": 334,
833
+ "¦": 335,
834
+ "§": 336,
835
+ "¨": 337,
836
+ "©": 338,
837
+ "ª": 339,
838
+ "«": 340,
839
+ "¬": 341,
840
+ "­": 342,
841
+ "®": 343,
842
+ "¯": 344,
843
+ "°": 345,
844
+ "±": 346,
845
+ "²": 347,
846
+ "³": 348,
847
+ "´": 349,
848
+ "µ": 350,
849
+ "¶": 351,
850
+ "·": 352,
851
+ "¸": 353,
852
+ "¹": 354,
853
+ "º": 355,
854
+ "»": 356,
855
+ "¼": 357,
856
+ "½": 358,
857
+ "¾": 359,
858
+ "¿": 360,
859
+ "À": 361,
860
+ "Á": 362,
861
+ "Â": 363,
862
+ "Ã": 364,
863
+ "Ä": 365,
864
+ "Å": 366,
865
+ "Æ": 367,
866
+ "Ç": 368,
867
+ "È": 369,
868
+ "É": 370,
869
+ "Ê": 371,
870
+ "Ë": 372,
871
+ "Ì": 373,
872
+ "Í": 374,
873
+ "Î": 375,
874
+ "Ï": 376,
875
+ "Ð": 377,
876
+ "Ñ": 378,
877
+ "Ò": 379,
878
+ "Ó": 380,
879
+ "Ô": 381,
880
+ "Õ": 382,
881
+ "Ö": 383,
882
+ "×": 384,
883
+ "Ø": 385,
884
+ "Ù": 386,
885
+ "Ú": 387,
886
+ "Û": 388,
887
+ "Ü": 389,
888
+ "Ý": 390,
889
+ "Þ": 391,
890
+ "ß": 392,
891
+ "à": 393,
892
+ "á": 394,
893
+ "â": 395,
894
+ "ã": 396,
895
+ "ä": 397,
896
+ "å": 398,
897
+ "æ": 399,
898
+ "ç": 400,
899
+ "è": 401,
900
+ "é": 402,
901
+ "ê": 403,
902
+ "ë": 404,
903
+ "ì": 405,
904
+ "í": 406,
905
+ "î": 407,
906
+ "ï": 408,
907
+ "ð": 409,
908
+ "ñ": 410,
909
+ "ò": 411,
910
+ "ó": 412,
911
+ "ô": 413,
912
+ "õ": 414,
913
+ "ö": 415,
914
+ "÷": 416,
915
+ "ø": 417,
916
+ "ù": 418,
917
+ "ú": 419,
918
+ "û": 420,
919
+ "ü": 421,
920
+ "ý": 422,
921
+ "þ": 423,
922
+ "ÿ": 424,
923
+ "ɐ": 425,
924
+ "ɑ": 426,
925
+ "ɒ": 427,
926
+ "ɓ": 428,
927
+ "ɔ": 429,
928
+ "ɕ": 430,
929
+ "ɖ": 431,
930
+ "ɗ": 432,
931
+ "ɘ": 433,
932
+ "ə": 434,
933
+ "ɚ": 435,
934
+ "ɛ": 436,
935
+ "ɜ": 437,
936
+ "ɝ": 438,
937
+ "ɞ": 439,
938
+ "ɟ": 440,
939
+ "ɠ": 441,
940
+ "ɡ": 442,
941
+ "ɢ": 443,
942
+ "ɣ": 444,
943
+ "ɤ": 445,
944
+ "ɥ": 446,
945
+ "ɦ": 447,
946
+ "ɧ": 448,
947
+ "ɨ": 449,
948
+ "ɩ": 450,
949
+ "ɪ": 451,
950
+ "ɫ": 452,
951
+ "ɬ": 453,
952
+ "ɭ": 454,
953
+ "ɮ": 455,
954
+ "ɯ": 456,
955
+ "ɰ": 457,
956
+ "ɱ": 458,
957
+ "ɲ": 459,
958
+ "ɳ": 460,
959
+ "ɴ": 461,
960
+ "ɵ": 462,
961
+ "ɶ": 463,
962
+ "ɷ": 464,
963
+ "ɸ": 465,
964
+ "ɹ": 466,
965
+ "ɺ": 467,
966
+ "ɻ": 468,
967
+ "ɼ": 469,
968
+ "ɽ": 470,
969
+ "ɾ": 471,
970
+ "ɿ": 472,
971
+ "ʀ": 473,
972
+ "ʁ": 474,
973
+ "ʂ": 475,
974
+ "ʃ": 476,
975
+ "ʄ": 477,
976
+ "ʅ": 478,
977
+ "ʆ": 479,
978
+ "ʇ": 480,
979
+ "ʈ": 481,
980
+ "ʉ": 482,
981
+ "ʊ": 483,
982
+ "ʋ": 484,
983
+ "ʌ": 485,
984
+ "ʍ": 486,
985
+ "ʎ": 487,
986
+ "ʏ": 488,
987
+ "ʐ": 489,
988
+ "ʑ": 490,
989
+ "ʒ": 491,
990
+ "ʓ": 492,
991
+ "ʔ": 493,
992
+ "ʕ": 494,
993
+ "ʖ": 495,
994
+ "ʗ": 496,
995
+ "ʘ": 497,
996
+ "ʙ": 498,
997
+ "ʚ": 499,
998
+ "ʛ": 500,
999
+ "ʜ": 501,
1000
+ "ʝ": 502,
1001
+ "ʞ": 503,
1002
+ "ʟ": 504,
1003
+ "ʠ": 505,
1004
+ "ʡ": 506,
1005
+ "ʢ": 507,
1006
+ "ʣ": 508,
1007
+ "ʤ": 509,
1008
+ "ʥ": 510,
1009
+ "ʦ": 511,
1010
+ "ʧ": 512,
1011
+ "ʨ": 513,
1012
+ "ʩ": 514,
1013
+ "ʪ": 515,
1014
+ "ʫ": 516,
1015
+ "ʬ": 517,
1016
+ "ʭ": 518,
1017
+ "ʮ": 519,
1018
+ "ʯ": 520,
1019
+ "ʰ": 521,
1020
+ "ʱ": 522,
1021
+ "ʲ": 523,
1022
+ "ʳ": 524,
1023
+ "ʴ": 525,
1024
+ "ʵ": 526,
1025
+ "ʶ": 527,
1026
+ "ʷ": 528,
1027
+ "ʸ": 529,
1028
+ "ʹ": 530,
1029
+ "ʺ": 531,
1030
+ "ʻ": 532,
1031
+ "ʼ": 533,
1032
+ "ʽ": 534,
1033
+ "ʾ": 535,
1034
+ "ʿ": 536,
1035
+ "ˀ": 537,
1036
+ "ˁ": 538,
1037
+ "˂": 539,
1038
+ "˃": 540,
1039
+ "˄": 541,
1040
+ "˅": 542,
1041
+ "ˆ": 543,
1042
+ "ˇ": 544,
1043
+ "ˈ": 545,
1044
+ "ˉ": 546,
1045
+ "ˊ": 547,
1046
+ "ˋ": 548,
1047
+ "ˌ": 549,
1048
+ "ˍ": 550,
1049
+ "ˎ": 551,
1050
+ "ˏ": 552,
1051
+ "ː": 553,
1052
+ "ˑ": 554,
1053
+ "˒": 555,
1054
+ "˓": 556,
1055
+ "˔": 557,
1056
+ "˕": 558,
1057
+ "˖": 559,
1058
+ "˗": 560,
1059
+ "˘": 561,
1060
+ "˙": 562,
1061
+ "˚": 563,
1062
+ "˛": 564,
1063
+ "˜": 565,
1064
+ "˝": 566,
1065
+ "˞": 567,
1066
+ "˟": 568,
1067
+ "ˠ": 569,
1068
+ "ˡ": 570,
1069
+ "ˢ": 571,
1070
+ "ˣ": 572,
1071
+ "ˤ": 573,
1072
+ "˥": 574,
1073
+ "˦": 575,
1074
+ "˧": 576,
1075
+ "˨": 577,
1076
+ "˩": 578,
1077
+ "˪": 579,
1078
+ "˫": 580,
1079
+ "ˬ": 581,
1080
+ "˭": 582,
1081
+ "ˮ": 583,
1082
+ "˯": 584,
1083
+ "˰": 585,
1084
+ "˱": 586,
1085
+ "˲": 587,
1086
+ "˳": 588,
1087
+ "˴": 589,
1088
+ "˵": 590,
1089
+ "˶": 591,
1090
+ "˷": 592,
1091
+ "˸": 593,
1092
+ "˹": 594,
1093
+ "˺": 595,
1094
+ "˻": 596,
1095
+ "˼": 597,
1096
+ "˽": 598,
1097
+ "˾": 599,
1098
+ "˿": 600,
1099
+ "ā": 601,
1100
+ "ō": 602,
1101
+ "…": 603,
1102
+ "[UH]": 604,
1103
+ "[UM]": 605,
1104
+ "[giggle]": 606,
1105
+ "[laughter]": 607,
1106
+ "[guffaw]": 608,
1107
+ "[inhale]": 609,
1108
+ "[exhale]": 610,
1109
+ "[sigh]": 611,
1110
+ "[cry]": 612,
1111
+ "[bark]": 613,
1112
+ "[howl]": 614,
1113
+ "[meow]": 615,
1114
+ "[singing]": 616,
1115
+ "[music]": 617,
1116
+ "[whistle]": 618,
1117
+ "[humming]": 619,
1118
+ "[gasp]": 620,
1119
+ "[groan]": 621,
1120
+ "[whisper]": 622,
1121
+ "[mumble]": 623,
1122
+ "[sniff]": 624,
1123
+ "[sneeze]": 625,
1124
+ "[cough]": 626,
1125
+ "[snore]": 627,
1126
+ "[chew]": 628,
1127
+ "[sip]": 629,
1128
+ "[clear_throat]": 630,
1129
+ "[kiss]": 631,
1130
+ "[shhh]": 632,
1131
+ "[gibberish]": 633,
1132
+ "[fr]": 634,
1133
+ "[es]": 635,
1134
+ "[de]": 636,
1135
+ "[it]": 637,
1136
+ "[ipa]": 638,
1137
+ "[end_of_label]": 639,
1138
+ "ŋ": 640,
1139
+ "ᵻ": 641,
1140
+ "θ": 642,
1141
+ "̩": 643,
1142
+ "̃": 644,
1143
+ "ɑː": 645,
1144
+ "iː": 646,
1145
+ "uː": 647,
1146
+ "ɜː": 648,
1147
+ "ɔː": 649,
1148
+ "oː": 650,
1149
+ "eɪ": 651,
1150
+ "oʊ": 652,
1151
+ "aɪ": 653,
1152
+ "aʊ": 654,
1153
+ "ɔɪ": 655,
1154
+ "dʒ": 656,
1155
+ "tʃ": 657,
1156
+ "ɪŋ": 658,
1157
+ "ᵻd": 659,
1158
+ "ˈiː": 660,
1159
+ "ˌiː": 661,
1160
+ "ˈɪ": 662,
1161
+ "ˌɪ": 663,
1162
+ "ˈeɪ": 664,
1163
+ "ˌeɪ": 665,
1164
+ "ˈɛ": 666,
1165
+ "ˌɛ": 667,
1166
+ "ˈæ": 668,
1167
+ "ˌæ": 669,
1168
+ "ˈɑː": 670,
1169
+ "ˌɑː": 671,
1170
+ "ˈɔː": 672,
1171
+ "ˌɔː": 673,
1172
+ "oːɹ": 674,
1173
+ "ˈoːɹ": 675,
1174
+ "ˌoːɹ": 676,
1175
+ "ˈoʊ": 677,
1176
+ "ˌoʊ": 678,
1177
+ "ˈʊ": 679,
1178
+ "ˌʊ": 680,
1179
+ "ˈuː": 681,
1180
+ "ˌuː": 682,
1181
+ "ˈɜː": 683,
1182
+ "ˌɜː": 684,
1183
+ "ˈʌ": 685,
1184
+ "ˌʌ": 686,
1185
+ "ˈaɪ": 687,
1186
+ "ˌaɪ": 688,
1187
+ "ˈaʊ": 689,
1188
+ "ˌaʊ": 690,
1189
+ "ˈɔɪ": 691,
1190
+ "ˌɔɪ": 692,
1191
+ "ˈɚ": 693,
1192
+ "ˌɐ": 694,
1193
+ "[PLACEHOLDER55]": 695,
1194
+ "[PLACEHOLDER56]": 696,
1195
+ "[PLACEHOLDER57]": 697,
1196
+ "[PLACEHOLDER58]": 698,
1197
+ "[PLACEHOLDER59]": 699,
1198
+ "[PLACEHOLDER60]": 700,
1199
+ "[PLACEHOLDER61]": 701,
1200
+ "[PLACEHOLDER62]": 702,
1201
+ "[PLACEHOLDER63]": 703,
1202
+ "<c_click>": 704,
1203
+ "<x_click>": 705,
1204
+ "<q_click>": 706,
1205
+ "[xh]": 707,
1206
+ "ć": 708,
1207
+ "Ⴀ": 709,
1208
+ "Ⴁ": 710,
1209
+ "Ⴂ": 711,
1210
+ "Ⴃ": 712,
1211
+ "Ⴄ": 713,
1212
+ "Ⴆ": 714,
1213
+ "Ⴈ": 715,
1214
+ "Ⴉ": 716,
1215
+ "Ⴊ": 717,
1216
+ "Ⴋ": 718,
1217
+ "Ⴌ": 719,
1218
+ "Ⴍ": 720,
1219
+ "Ⴎ": 721,
1220
+ "Ⴐ": 722,
1221
+ "Ⴑ": 723,
1222
+ "Ⴒ": 724,
1223
+ "Ⴓ": 725,
1224
+ "Ⴔ": 726,
1225
+ "Ⴕ": 727,
1226
+ "Ⴗ": 728,
1227
+ "Ⴟ": 729,
1228
+ "Ⴠ": 730,
1229
+ "ა": 731,
1230
+ "ბ": 732,
1231
+ "გ": 733,
1232
+ "დ": 734,
1233
+ "ე": 735,
1234
+ "ვ": 736,
1235
+ "ზ": 737,
1236
+ "ი": 738,
1237
+ "კ": 739,
1238
+ "ლ": 740,
1239
+ "მ": 741,
1240
+ "ნ": 742,
1241
+ "ო": 743,
1242
+ "პ": 744,
1243
+ "რ": 745,
1244
+ "ს": 746,
1245
+ "ტ": 747,
1246
+ "უ": 748,
1247
+ "ფ": 749,
1248
+ "ქ": 750,
1249
+ "ყ": 751,
1250
+ "ც": 752,
1251
+ "წ": 753,
1252
+ "ხ": 754,
1253
+ "ჯ": 755,
1254
+ "ჰ": 756,
1255
+ "": 757,
1256
+ "კუ": 758,
1257
+ "ან": 759,
1258
+ "ელ": 760,
1259
+ "ენ": 761,
1260
+ "ზი": 762,
1261
+ "წა": 763,
1262
+ "ბა": 764,
1263
+ "ნგ": 765,
1264
+ "ტჰ": 766,
1265
+ "სი": 767,
1266
+ "ლა": 768,
1267
+ "ინ": 769,
1268
+ "მა": 770,
1269
+ "პჰ": 771,
1270
+ "ის": 772,
1271
+ "კჰ": 773,
1272
+ "კა": 774,
1273
+ "ლო": 775,
1274
+ "ყო": 776,
1275
+ "წე": 777,
1276
+ "ლუ": 778,
1277
+ "ყა": 779,
1278
+ "ლე": 780,
1279
+ "კო": 781,
1280
+ "უკუ": 782,
1281
+ "ონ": 783,
1282
+ "ყე": 784,
1283
+ "ოკუ": 785,
1284
+ "ზა": 786,
1285
+ "ელა": 787,
1286
+ "უმ": 788,
1287
+ "ლი": 789,
1288
+ "სჰ": 790,
1289
+ "ანგ": 791,
1290
+ "ნგა": 792,
1291
+ "სე": 793,
1292
+ "ნა": 794,
1293
+ "ეზი": 795,
1294
+ "კწა": 796,
1295
+ "ელე": 797,
1296
+ "კწ": 798,
1297
+ "ანა": 799,
1298
+ "და": 800,
1299
+ "ბუ": 801,
1300
+ "ბე": 802,
1301
+ "ტჰი": 803,
1302
+ "უნ": 804,
1303
+ "ყი": 805,
1304
+ "კე": 806,
1305
+ "დი": 807,
1306
+ "სა": 808,
1307
+ "ბან": 809,
1308
+ "ენი": 810,
1309
+ "ბო": 811,
1310
+ "ჰა": 812,
1311
+ "ემ": 813,
1312
+ "პჰა": 814,
1313
+ "ნტ": 815,
1314
+ "ომ": 816,
1315
+ "ტჰა": 817,
1316
+ "ელო": 818,
1317
+ "ისა": 819,
1318
+ "ენგ": 820,
1319
+ "ზე": 821,
1320
+ "ამა": 822,
1321
+ "კჰო": 823,
1322
+ "ზო": 824,
1323
+ "ტსჰ": 825,
1324
+ "ჰლა": 826,
1325
+ "იმ": 827,
1326
+ "ანგა": 828,
1327
+ "ესი": 829,
1328
+ "კწე": 830,
1329
+ "ტჰე": 831,
1330
+ "ულუ": 832,
1331
+ "ბი": 833,
1332
+ "ინი": 834,
1333
+ "ელი": 835,
1334
+ "უკუბა": 836,
1335
+ "აბა": 837,
1336
+ "ენზი": 838,
1337
+ "ანდ": 839,
1338
+ "კი": 840,
1339
+ "ისე": 841,
1340
+ "დო": 842,
1341
+ "ლწა": 843,
1342
+ "ფუნ": 844,
1343
+ "იზი": 845,
1344
+ "ნე": 846,
1345
+ "ბონ": 847,
1346
+ "ისი": 848,
1347
+ "ტჰუ": 849,
1348
+ "ინტ": 850,
1349
+ "ხა": 851,
1350
+ "წუ": 852,
1351
+ "ისო": 853,
1352
+ "წო": 854,
1353
+ "კუბა": 855,
1354
+ "ლეყო": 856,
1355
+ "ენტ": 857,
1356
+ "ნგო": 858,
1357
+ "ანე": 859,
1358
+ "ნოკუ": 860,
1359
+ "ვა": 861,
1360
+ "ჰო": 862,
1361
+ "ნჯ": 863,
1362
+ "ნო": 864,
1363
+ "კან": 865,
1364
+ "ქა": 866,
1365
+ "ბანტ": 867,
1366
+ "კჰე": 868,
1367
+ "ნგოკუ": 869,
1368
+ "კუნ": 870,
1369
+ "მი": 871,
1370
+ "კჰა": 872,
1371
+ "ტყ": 873,
1372
+ "ელწა": 874,
1373
+ "ნგე": 875,
1374
+ "ცე": 876,
1375
+ "ფუ": 877,
1376
+ "კჰუ": 878,
1377
+ "ტჰო": 879,
1378
+ "პჰუ": 880,
1379
+ "პჰე": 881,
1380
+ "ცა": 882,
1381
+ "სებ": 883,
1382
+ "ქუ": 884,
1383
+ "სო": 885,
1384
+ "ჰლ": 886,
1385
+ "ჰუ": 887,
1386
+ "ლელა": 888,
1387
+ "ნტო": 889,
1388
+ "ნი": 890,
1389
+ "მან": 891,
1390
+ "ენე": 892,
1391
+ "ქო": 893,
1392
+ "ესჰ": 894,
1393
+ "ბანტუ": 895,
1394
+ "ანტ": 896,
1395
+ "კჰულუ": 897,
1396
+ "დლა": 898,
1397
+ "ისწა": 899,
1398
+ "ონა": 900,
1399
+ "ოლუ": 901,
1400
+ "ენზა": 902,
1401
+ "ქი": 903,
1402
+ "ჰლო": 904,
1403
+ "ლწ": 905,
1404
+ "კწი": 906,
1405
+ "ფა": 907,
1406
+ "ეკუ": 908,
1407
+ "ლოკუ": 909,
1408
+ "მო": 910,
1409
+ "დე": 911,
1410
+ "ნდი": 912,
1411
+ "პჰო": 913,
1412
+ "ელწე": 914,
1413
+ "ლუნგ": 915,
1414
+ "ვუ": 916,
1415
+ "პჰი": 917,
1416
+ "ტი": 918,
1417
+ "ბჰა": 919,
1418
+ "ფი": 920,
1419
+ "ლწე": 921,
1420
+ "ტყა": 922,
1421
+ "ყოკუ": 923,
1422
+ "ზწე": 924,
1423
+ "სებენზი": 925,
1424
+ "ნტუ": 926,
1425
+ "სუ": 927,
1426
+ "ენა": 928,
1427
+ "ცი": 929,
1428
+ "ნდ": 930,
1429
+ "წანა": 931,
1430
+ "ფუმ": 932,
1431
+ "ელელა": 933,
1432
+ "კუმ": 934,
1433
+ "ანი": 935,
1434
+ "ბჰ": 936,
1435
+ "ენდ": 937,
1436
+ "იმი": 938,
1437
+ "ზოკუ": 939,
1438
+ "ტსჰა": 940,
1439
+ "ანტსი": 941,
1440
+ "კილეყო": 942,
1441
+ "ელელე": 943,
1442
+ "წენი": 944,
1443
+ "ნჯენგ": 945,
1444
+ "ბონა": 946,
1445
+ "გა": 947,
1446
+ "მბა": 948,
1447
+ "ინა": 949,
1448
+ "ონკე": 950,
1449
+ "დწა": 951,
1450
+ "პა": 952,
1451
+ "ესჰა": 953,
1452
+ "წან": 954,
1453
+ "ჯო": 955,
1454
+ "ნგუ": 956,
1455
+ "იინ": 957,
1456
+ "ჰლუ": 958,
1457
+ "ლოო": 959,
1458
+ "მბი": 960,
1459
+ "კანყე": 961,
1460
+ "ხესჰა": 962,
1461
+ "ხო": 963,
1462
+ "ჰლე": 964,
1463
+ "გქი": 965,
1464
+ "ფუნა": 966,
1465
+ "ფუნე": 967,
1466
+ "ხჰო": 968,
1467
+ "ანდა": 969,
1468
+ "ნყე": 970,
1469
+ "ლისა": 971,
1470
+ "ცო": 972,
1471
+ "გუ": 973,
1472
+ "ქჰუ": 974,
1473
+ "რჰ": 975,
1474
+ "აკუ": 976,
1475
+ "ინზი": 977,
1476
+ "ნყ": 978,
1477
+ "ენგა": 979,
1478
+ "ემი": 980,
1479
+ "წეყო": 981,
1480
+ "ინტო": 982,
1481
+ "გც": 983,
1482
+ "ულუმ": 984,
1483
+ "ნამა": 985,
1484
+ "ცჰა": 986,
1485
+ "ენკო": 987,
1486
+ "ინგ": 988,
1487
+ "მპ": 989,
1488
+ "ტა": 990,
1489
+ "ლელე": 991,
1490
+ "კწაზი": 992,
1491
+ "ტჰწა": 993,
1492
+ "კუნყე": 994,
1493
+ "ენზე": 995,
1494
+ "ანდლა": 996,
1495
+ "ნომ": 997,
1496
+ "სელე": 998,
1497
+ "პჰაკა": 999,
1498
+ "აბანტუ": 1000,
1499
+ "ონდო": 1001,
1500
+ "ნეზი": 1002,
1501
+ "კომ": 1003,
1502
+ "ლაწუ": 1004,
1503
+ "ელელ": 1005,
1504
+ "ინდ": 1006,
1505
+ "ზუ": 1007,
1506
+ "ენდა": 1008,
1507
+ "პჰუმ": 1009,
1508
+ "ანგო": 1010,
1509
+ "ასი": 1011,
1510
+ "დოდა": 1012,
1511
+ "ისჰ": 1013,
1512
+ "ენტე": 1014,
1513
+ "უბუ": 1015,
1514
+ "ბინი": 1016,
1515
+ "ფო": 1017,
1516
+ "ოკანყე": 1018,
1517
+ "ელელო": 1019,
1518
+ "სეტყ": 1020,
1519
+ "უყა": 1021,
1520
+ "ზელა": 1022,
1521
+ "ტო": 1023,
1522
+ "სოკუ": 1024,
1523
+ "ნჯე": 1025,
1524
+ "ქინ": 1026,
1525
+ "წანო": 1027,
1526
+ "მალი": 1028,
1527
+ "ფუნეკა": 1029,
1528
+ "ცუ": 1030,
1529
+ "ტსჰო": 1031,
1530
+ "ცჰ": 1032,
1531
+ "ცწა": 1033,
1532
+ "ტჰეტჰა": 1034,
1533
+ "რჰულუმ": 1035,
1534
+ "ნგამა": 1036,
1535
+ "გო": 1037,
1536
+ "კუმა": 1038,
1537
+ "ჰლალა": 1039,
1538
+ "ფან": 1040,
1539
+ "ლენი": 1041,
1540
+ "აყი": 1042,
1541
+ "კქუ": 1043,
1542
+ "კილე": 1044,
1543
+ "ფანა": 1045,
1544
+ "უმა": 1046,
1545
+ "კჰი": 1047,
1546
+ "კუკუ": 1048,
1547
+ "პჰანტსი": 1049,
1548
+ "გამა": 1050,
1549
+ "წაყე": 1051,
1550
+ "ნგენ": 1052,
1551
+ "ყამა": 1053,
1552
+ "კწან": 1054,
1553
+ "ონო": 1055,
1554
+ "მე": 1056,
1555
+ "ონდ": 1057,
1556
+ "ინდა": 1058,
1557
+ "ყაკა": 1059,
1558
+ "ზულუ": 1060,
1559
+ "იკა": 1061,
1560
+ "ლანდ": 1062,
1561
+ "აბან": 1063,
1562
+ "აპჰო": 1064,
1563
+ "დალა": 1065,
1564
+ "ნგუმ": 1066,
1565
+ "ოკო": 1067,
1566
+ "სწა": 1068,
1567
+ "იი": 1069,
1568
+ "ონი": 1070,
1569
+ "პი": 1071,
1570
+ "სისი": 1072,
1571
+ "ინკო": 1073,
1572
+ "კჰონა": 1074,
1573
+ "კწეზი": 1075,
1574
+ "ბანგა": 1076,
1575
+ "პჰამბი": 1077,
1576
+ "კქუბო": 1078,
1577
+ "ლელო": 1079,
1578
+ "აკა": 1080,
1579
+ "ეს": 1081,
1580
+ "კწაყე": 1082,
1581
+ "ალო": 1083,
1582
+ "ბანგ": 1084,
1583
+ "კოდწა": 1085,
1584
+ "ბენზი": 1086,
1585
+ "ანდი": 1087,
1586
+ "იიმ": 1088,
1587
+ "იყა": 1089,
1588
+ "კელე": 1090,
1589
+ "ქესჰ": 1091,
1590
+ "ვუმ": 1092,
1591
+ "რჰულუმენტე": 1093,
1592
+ "სეტყენზი": 1094,
1593
+ "ჰლაბა": 1095,
1594
+ "ნესი": 1096,
1595
+ "ნდა": 1097,
1596
+ "ხი": 1098,
1597
+ "უკუნ": 1099,
1598
+ "ფუმანა": 1100,
1599
+ "ქინისე": 1101,
1600
+ "ობუ": 1102,
1601
+ "ქჰ": 1103,
1602
+ "კუკჰო": 1104,
1603
+ "ელუ": 1105,
1604
+ "ბანტწანა": 1106,
1605
+ "ხჰ": 1107,
1606
+ "ყან": 1108,
1607
+ "კოლო": 1109,
1608
+ "ტჰუბა": 1110,
1609
+ "მბ": 1111,
1610
+ "კალა": 1112,
1611
+ "ქალა": 1113,
1612
+ "ფიკა": 1114,
1613
+ "ამან": 1115,
1614
+ "ფუნდო": 1116,
1615
+ "ნენ": 1117,
1616
+ "ედ": 1118,
1617
+ "ქე": 1119,
1618
+ "ბულა": 1120,
1619
+ "ზწა": 1121,
1620
+ "კწამა": 1122,
1621
+ "ისებენზი": 1123,
1622
+ "ფანელე": 1124,
1623
+ "ლის": 1125,
1624
+ "პჰანდ": 1126,
1625
+ "ეზა": 1127,
1626
+ "უმნტუ": 1128,
1627
+ "პჰუჰლ": 1129,
1628
+ "ნაბა": 1130,
1629
+ "ამ": 1131,
1630
+ "იინტ": 1132,
1631
+ "ქჰა": 1133,
1632
+ "სელა": 1134,
1633
+ "ყინ": 1135,
1634
+ "წოკუ": 1136,
1635
+ "ხჰა": 1137,
1636
+ "ზინ": 1138,
1637
+ "დუ": 1139,
1638
+ "სემ": 1140,
1639
+ "ჯი": 1141,
1640
+ "კელა": 1142,
1641
+ "ლინგ": 1143,
1642
+ "ლულე": 1144,
1643
+ "ზწ": 1145,
1644
+ "ლისე": 1146,
1645
+ "ლოკო": 1147,
1646
+ "ემა": 1148,
1647
+ "ზანტსი": 1149,
1648
+ "კწესი": 1150,
1649
+ "პო": 1151,
1650
+ "ელინ": 1152,
1651
+ "ტჰანდა": 1153,
1652
+ "კწენზა": 1154,
1653
+ "რო": 1155,
1654
+ "პჰაკატჰი": 1156,
1655
+ "პჰელა": 1157,
1656
+ "წანგ": 1158,
1657
+ "ბელე": 1159,
1658
+ "ტჰეტჰო": 1160,
1659
+ "ენდლელა": 1161,
1660
+ "ფუნდი": 1162,
1661
+ "ეყა": 1163,
1662
+ "კწენ": 1164,
1663
+ "ზამა": 1165,
1664
+ "ტყე": 1166,
1665
+ "კულუ": 1167,
1666
+ "კაყო": 1168,
1667
+ "ინგა": 1169,
1668
+ "ლაყო": 1170,
1669
+ "ყესი": 1171,
1670
+ "ჯონგ": 1172,
1671
+ "კისა": 1173,
1672
+ "ტუ": 1174,
1673
+ "წენ": 1175,
1674
+ "კაზი": 1176,
1675
+ "უტჰი": 1177,
1676
+ "ბანდა": 1178,
1677
+ "ნზო": 1179,
1678
+ "სანა": 1180,
1679
+ "უნგა": 1181,
1680
+ "ნოკუბა": 1182,
1681
+ "წანე": 1183,
1682
+ "კაკჰულუ": 1184,
1683
+ "კანტი": 1185,
1684
+ "ცედ": 1186,
1685
+ "ნემ": 1187,
1686
+ "წატჰი": 1188,
1687
+ "ომა": 1189,
1688
+ "ნანგ": 1190,
1689
+ "ნკე": 1191,
1690
+ "უტსჰ": 1192,
1691
+ "ცწანგ": 1193,
1692
+ "ბალა": 1194,
1693
+ "ლომ": 1195,
1694
+ "სებენზა": 1196,
1695
+ "აზი": 1197,
1696
+ "ყაზი": 1198,
1697
+ "კწისი": 1199,
1698
+ "ცწადი": 1200,
1699
+ "იზა": 1201,
1700
+ "კუფუნეკა": 1202,
1701
+ "კუტჰი": 1203,
1702
+ "ბენ": 1204,
1703
+ "წონკე": 1205,
1704
+ "ელანა": 1206,
1705
+ "ბჰუ": 1207,
1706
+ "სომ": 1208,
1707
+ "უნყ": 1209,
1708
+ "ცწანგც": 1210,
1709
+ "უკწა": 1211,
1710
+ "ნგამ": 1212,
1711
+ "კანგა": 1213,
1712
+ "სენ": 1214,
1713
+ "ანყ": 1215,
1714
+ "ეზინ": 1216,
1715
+ "რა": 1217,
1716
+ "ნასე": 1218,
1717
+ "ნჯალო": 1219,
1718
+ "კჰაყა": 1220,
1719
+ "ტჰემ": 1221,
1720
+ "ჰამბა": 1222,
1721
+ "ჰლობო": 1223,
1722
+ "ზელე": 1224,
1723
+ "მბო": 1225,
1724
+ "ბეკა": 1226,
1725
+ "ლუნგუ": 1227,
1726
+ "ხე": 1228,
1727
+ "ყაყი": 1229,
1728
+ "სესი": 1230,
1729
+ "კწიზი": 1231,
1730
+ "ზეზი": 1232,
1731
+ "ლინ": 1233,
1732
+ "ცინ": 1234,
1733
+ "ლანდელა": 1235,
1734
+ "ზანა": 1236,
1735
+ "სჰო": 1237,
1736
+ "ველა": 1238,
1737
+ "აპჰა": 1239,
1738
+ "უყე": 1240,
1739
+ "ყომ": 1241,
1740
+ "კწანოკუ": 1242,
1741
+ "ვო": 1243,
1742
+ "ემვა": 1244,
1743
+ "ებუ": 1245,
1744
+ "კოკუ": 1246,
1745
+ "წამ": 1247,
1746
+ "კულე": 1248,
1747
+ "ბენი": 1249,
1748
+ "რჰა": 1250,
1749
+ "კელო": 1251,
1750
+ "ტჰატჰა": 1252,
1751
+ "ენზიწა": 1253,
1752
+ "ხჰოსა": 1254,
1753
+ "ბჰო": 1255,
1754
+ "ისწე": 1256,
1755
+ "ცალა": 1257,
1756
+ "ლუნგა": 1258,
1757
+ "ლისი": 1259,
1758
+ "კუნგა": 1260,
1759
+ "პჰანდლე": 1261,
1760
+ "ზემ": 1262,
1761
+ "ლწენი": 1263,
1762
+ "პჰამბილი": 1264,
1763
+ "ბელა": 1265,
1764
+ "ზელ": 1266,
1765
+ "ილე": 1267,
1766
+ "უვა": 1268,
1767
+ "სეტყენზისწა": 1269,
1768
+ "ლელ": 1270,
1769
+ "უკუზი": 1271,
1770
+ "სჰი": 1272,
1771
+ "ნგაბა": 1273,
1772
+ "სუკა": 1274,
1773
+ "კელელა": 1275,
1774
+ "ყუ": 1276,
1775
+ "კალოკუ": 1277,
1776
+ "ყამ": 1278,
1777
+ "სჰისჰ": 1279,
1778
+ "ელეყო": 1280,
1779
+ "ცედა": 1281,
1780
+ "წაბა": 1282,
1781
+ "ფუმანე": 1283,
1782
+ "ბუმ": 1284,
1783
+ "კწიმ": 1285,
1784
+ "სუკუ": 1286,
1785
+ "კაკუ": 1287,
1786
+ "ესა": 1288,
1787
+ "ნგომ": 1289,
1788
+ "ნამ": 1290,
1789
+ "ინკოსი": 1291,
1790
+ "ტჰილე": 1292,
1791
+ "ენეყო": 1293,
1792
+ "ლელწა": 1294,
1793
+ "ლულა": 1295,
1794
+ "პჰატჰა": 1296,
1795
+ "ეტჰო": 1297,
1796
+ "უკუზე": 1298,
1797
+ "პჰუმა": 1299,
1798
+ "კისო": 1300,
1799
+ "ფრ": 1301,
1800
+ "ყენ": 1302,
1801
+ "ყისე": 1303,
1802
+ "მანზი": 1304,
1803
+ "ანგე": 1305,
1804
+ "კჰატჰა": 1306,
1805
+ "პილო": 1307,
1806
+ "ჯე": 1308,
1807
+ "კამ": 1309,
1808
+ "ინდაწო": 1310,
1809
+ "ვე": 1311,
1810
+ "ზონკე": 1312,
1811
+ "ფრიკა": 1313,
1812
+ "კწინ": 1314,
1813
+ "ბონკე": 1315,
1814
+ "წალა": 1316,
1815
+ "იზინტო": 1317,
1816
+ "ზომ": 1318,
1817
+ "კარჰულუმენტე": 1319,
1818
+ "ტჰენგ": 1320,
1819
+ "ფუნდა": 1321,
1820
+ "ნტწანა": 1322,
1821
+ "ტჰწე": 1323,
1822
+ "ლანგა": 1324,
1823
+ "ცწანგცისო": 1325,
1824
+ "კანა": 1326,
1825
+ "ზიზი": 1327,
1826
+ "წაზი": 1328,
1827
+ "Ⴌგ": 1329,
1828
+ "სჰე": 1330,
1829
+ "ჰლაწუ": 1331,
1830
+ "ტყალა": 1332,
1831
+ "აბე": 1333,
1832
+ "გი": 1334,
1833
+ "ულო": 1335,
1834
+ "პჰეზულუ": 1336,
1835
+ "რი": 1337,
1836
+ "უბა": 1338,
1837
+ "ჰლწა": 1339,
1838
+ "ფამა": 1340,
1839
+ "ნალო": 1341,
1840
+ "კწაკუ": 1342,
1841
+ "დოლო": 1343,
1842
+ "ლწაზი": 1344,
1843
+ "ზენ": 1345,
1844
+ "წამა": 1346,
1845
+ "ნაკუ": 1347,
1846
+ "ნობუ": 1348,
1847
+ "პჰუჰლისო": 1349,
1848
+ "���წი": 1350,
1849
+ "ზიკო": 1351,
1850
+ "ოკუბა": 1352,
1851
+ "ენზიწე": 1353,
1852
+ "ბანდლა": 1354,
1853
+ "ბისი": 1355,
1854
+ "ნეე": 1356,
1855
+ "ქონ": 1357,
1856
+ "ცანდ": 1358,
1857
+ "ყაკუ": 1359,
1858
+ "პჰეზუ": 1360,
1859
+ "ტე": 1361,
1860
+ "ნგეზი": 1362,
1861
+ "გუნ": 1363,
1862
+ "ტჰუმ": 1364,
1863
+ "უნი": 1365,
1864
+ "ქონდო": 1366,
1865
+ "ყოკუბა": 1367,
1866
+ "იინკო": 1368,
1867
+ "ცჰაპჰა": 1369,
1868
+ "სჰუ": 1370,
1869
+ "ფუნდ": 1371,
1870
+ "გუქუ": 1372,
1871
+ "აყე": 1373,
1872
+ "ეკო": 1374,
1873
+ "კწაბა": 1375,
1874
+ "ტჰინი": 1376,
1875
+ "ქექესჰ": 1377,
1876
+ "ბაზი": 1378,
1877
+ "ზამ": 1379,
1878
+ "ანგან": 1380,
1879
+ "ყეზი": 1381,
1880
+ "უზა": 1382,
1881
+ "ტჰინტ": 1383,
1882
+ "კჰუსელე": 1384,
1883
+ "ფე": 1385,
1884
+ "ყაკჰე": 1386,
1885
+ "ხჰობო": 1387,
1886
+ "ცოცე": 1388,
1887
+ "ლაკჰე": 1389,
1888
+ "ბანი": 1390,
1889
+ "კწემ": 1391,
1890
+ "ილეყო": 1392,
1891
+ "ხანდ": 1393,
1892
+ "კუყო": 1394,
1893
+ "უმზი": 1395,
1894
+ "ნგოკო": 1396,
1895
+ "ბჰედ": 1397,
1896
+ "ინდლელა": 1398,
1897
+ "სინი": 1399,
1898
+ "ინკ": 1400,
1899
+ "ყონა": 1401,
1900
+ "Ⴀფრიკა": 1402,
1901
+ "ინყაკა": 1403,
1902
+ "საპჰო": 1404,
1903
+ "ენტლა": 1405,
1904
+ "ელელწანო": 1406,
1905
+ "ლანდელაყო": 1407,
1906
+ "კელწა": 1408,
1907
+ "წაყო": 1409,
1908
+ "ბაბე": 1410,
1909
+ "ხაკი": 1411,
1910
+ "ელელეყო": 1412,
1911
+ "ენკონზო": 1413,
1912
+ "კაკუჰლე": 1414,
1913
+ "აწუ": 1415,
1914
+ "ბისო": 1416,
1915
+ "ლინი": 1417,
1916
+ "ნანგა": 1418,
1917
+ "ულა": 1419,
1918
+ "ყის": 1420,
1919
+ "ლონგ": 1421,
1920
+ "ენგე": 1422,
1921
+ "ნემი": 1423,
1922
+ "ენდი": 1424,
1923
+ "წაზა": 1425,
1924
+ "ბესი": 1426,
1925
+ "ლანა": 1427,
1926
+ "ენდაწო": 1428,
1927
+ "აბანგა": 1429,
1928
+ "ზინი": 1430,
1929
+ "კოკო": 1431,
1930
+ "ბანე": 1432,
1931
+ "ტჰეტჰ": 1433,
1932
+ "ქჰუბა": 1434,
1933
+ "ხანდუვა": 1435,
1934
+ "ველ": 1436,
1935
+ "ოყა": 1437,
1936
+ "რჰო": 1438,
1937
+ "კჰაწუ": 1439,
1938
+ "ქელა": 1440,
1939
+ "წელე": 1441,
1940
+ "პჰონდო": 1442,
1941
+ "პჰეპჰა": 1443,
1942
+ "ლაწულო": 1444,
1943
+ "ბალულე": 1445,
1944
+ "ლამ": 1446,
1945
+ "სებე": 1447,
1946
+ "ეზ": 1448,
1947
+ "ლისწა": 1449,
1948
+ "ლან": 1450,
1949
+ "ყატჰ": 1451,
1950
+ "უკუყი": 1452,
1951
+ "სჰა": 1453,
1952
+ "ლესი": 1454,
1953
+ "ქოქო": 1455,
1954
+ "ენზეკა": 1456,
1955
+ "ზინგა": 1457,
1956
+ "ვაკა": 1458,
1957
+ "კელწე": 1459,
1958
+ "წესი": 1460,
1959
+ "უკუტყა": 1461,
1960
+ "ბომი": 1462,
1961
+ "ჰამბ": 1463,
1962
+ "ხიბ": 1464,
1963
+ "ნგესი": 1465,
1964
+ "ისანა": 1466,
1965
+ "სჰისჰინი": 1467,
1966
+ "მანდლა": 1468,
1967
+ "ნონ": 1469,
1968
+ "ენტო": 1470,
1969
+ "ცედისა": 1471,
1970
+ "ლიკა": 1472,
1971
+ "აკუკჰო": 1473,
1972
+ "ქანა": 1474,
1973
+ "ყენა": 1475,
1974
+ "სინგა": 1476,
1975
+ "ყაბა": 1477,
1976
+ "ემპ": 1478,
1977
+ "ბონაკა": 1479,
1978
+ "გოსა": 1480,
1979
+ "ელინყე": 1481,
1980
+ "ბისა": 1482,
1981
+ "ილო": 1483,
1982
+ "ნინზი": 1484,
1983
+ "კუბე": 1485,
1984
+ "ნგაყო": 1486,
1985
+ "კჰალა": 1487,
1986
+ "ფაკა": 1488,
1987
+ "იწა": 1489,
1988
+ "ნგელი": 1490,
1989
+ "ყონკე": 1491,
1990
+ "დლალა": 1492,
1991
+ "ბჰე": 1493,
1992
+ "კჰიწო": 1494,
1993
+ "ცანდელო": 1495,
1994
+ "დუმ": 1496,
1995
+ "ნგენა": 1497,
1996
+ "აბამ": 1498,
1997
+ "დლალო": 1499,
1998
+ "ჯონგენე": 1500,
1999
+ "ზაყო": 1501,
2000
+ "ზიმა": 1502,
2001
+ "ზალი": 1503,
2002
+ "ომბი": 1504,
2003
+ "ლონგწანე": 1505,
2004
+ "გრ": 1506,
2005
+ "ყინტ": 1507,
2006
+ "კუყა": 1508,
2007
+ "სწე": 1509,
2008
+ "ელენი": 1510,
2009
+ "ზაბა": 1511,
2010
+ "ზატჰუ": 1512,
2011
+ "ბომ": 1513,
2012
+ "ქოქოსჰო": 1514,
2013
+ "მელა": 1515,
2014
+ "ქუმ": 1516,
2015
+ "ტჰატჰუ": 1517,
2016
+ "ებე": 1518,
2017
+ "ლისო": 1519,
2018
+ "ყელა": 1520,
2019
+ "ესიტჰი": 1521,
2020
+ "ფაზი": 1522,
2021
+ "ბონაკალა": 1523,
2022
+ "ცოცეკო": 1524,
2023
+ "Ⴉუ": 1525,
2024
+ "Ⴋზანტსი": 1526,
2025
+ "Ⴑი": 1527,
2026
+ "ასე": 1528,
2027
+ "ელელწა": 1529,
2028
+ "ენყე": 1530,
2029
+ "კჰუპჰა": 1531,
2030
+ "ლაწულა": 1532,
2031
+ "ცელო": 1533,
2032
+ "კწენი": 1534,
2033
+ "სებენზისა": 1535,
2034
+ "ბანდაკან": 1536,
2035
+ "ელწანო": 1537,
2036
+ "ზიმ": 1538,
2037
+ "ტჰელა": 1539,
2038
+ "ეზინყე": 1540,
2039
+ "ქუკა": 1541,
2040
+ "კჰიწა": 1542,
2041
+ "Ⴋა": 1543,
2042
+ "ჯწა": 1544,
2043
+ "კჰანგ": 1545,
2044
+ "წეტჰუ": 1546,
2045
+ "ამადოდა": 1547,
2046
+ "ლუნგისა": 1548,
2047
+ "ნდლუ": 1549,
2048
+ "ლინდ": 1550,
2049
+ "ტსა": 1551,
2050
+ "უსი": 1552,
2051
+ "მალუნგა": 1553,
2052
+ "დიბან": 1554,
2053
+ "ბანა": 1555,
2054
+ "ლილო": 1556,
2055
+ "00": 1557,
2056
+ "განგა": 1558,
2057
+ "კცუ": 1559,
2058
+ "სეკუ": 1560,
2059
+ "კჰუტჰა": 1561,
2060
+ "ცაც": 1562,
2061
+ "ლწინი": 1563,
2062
+ "ება": 1564,
2063
+ "ყოლუ": 1565,
2064
+ "კწამ": 1566,
2065
+ "ტსჰანე": 1567,
2066
+ "ცებო": 1568,
2067
+ "ლალა": 1569,
2068
+ "ლეკო": 1570,
2069
+ "კწაკჰე": 1571,
2070
+ "ვან": 1572,
2071
+ "ილი": 1573,
2072
+ "მნ": 1574,
2073
+ "ყანგა": 1575,
2074
+ "ისელო": 1576,
2075
+ "კჰუმ": 1577,
2076
+ "პჰატჰ": 1578,
2077
+ "კწეტჰუ": 1579,
2078
+ "გცინ": 1580,
2079
+ "ბაყა": 1581,
2080
+ "ტჰანდ": 1582,
2081
+ "კჰან": 1583,
2082
+ "ყიმ": 1584,
2083
+ "ცჰი": 1585,
2084
+ "ზელწა": 1586,
2085
+ "ნგელა": 1587,
2086
+ "ნოკო": 1588,
2087
+ "ზესი": 1589,
2088
+ "ელწეყო": 1590,
2089
+ "იბე": 1591,
2090
+ "რე": 1592,
2091
+ "უსა": 1593,
2092
+ "ყენი": 1594,
2093
+ "მასი": 1595,
2094
+ "გცინა": 1596,
2095
+ "აბანტწანა": 1597,
2096
+ "მნტუ": 1598,
2097
+ "სელწა": 1599,
2098
+ "ჯელო": 1600,
2099
+ "ყილე": 1601,
2100
+ "კჰოსი": 1602,
2101
+ "ეზო": 1603,
2102
+ "კულო": 1604,
2103
+ "კუპჰელა": 1605,
2104
+ "ყემ": 1606,
2105
+ "პჰალო": 1607,
2106
+ "ტსჰი": 1608,
2107
+ "კანი": 1609,
2108
+ "პაწუ": 1610,
2109
+ "პჰუმო": 1611,
2110
+ "უტჰიხო": 1612,
2111
+ "უკუმ": 1613,
2112
+ "უმნ": 1614,
2113
+ "ბუყა": 1615,
2114
+ "ნგეკჰო": 1616,
2115
+ "ელუნგ": 1617,
2116
+ "ფანელეკილეყო": 1618,
2117
+ "ზელწე": 1619,
2118
+ "იხესჰა": 1620,
2119
+ "წაბო": 1621,
2120
+ "ბამ": 1622,
2121
+ "სჰუმ": 1623,
2122
+ "ეზინგა": 1624,
2123
+ "გაქო": 1625,
2124
+ "ნგამელი": 1626,
2125
+ "იინგ": 1627,
2126
+ "კრ": 1628,
2127
+ "ბალი": 1629,
2128
+ "სეკო": 1630,
2129
+ "ნგენხა": 1631,
2130
+ "სონ": 1632,
2131
+ "ტყი": 1633,
2132
+ "ბასე": 1634,
2133
+ "ვუმა": 1635,
2134
+ "ხიბელელწანო": 1636,
2135
+ "ზიბე": 1637,
2136
+ "სინ": 1638,
2137
+ "კწემი": 1639,
2138
+ "კუმბი": 1640,
2139
+ "ბანგელა": 1641,
2140
+ "უბე": 1642,
2141
+ "კუდალა": 1643,
2142
+ "ლეკა": 1644,
2143
+ "ჰაყი": 1645,
2144
+ "ზონა": 1646,
2145
+ "წანგა": 1647,
2146
+ "ლუნგის": 1648,
2147
+ "ენკომო": 1649,
2148
+ "ლინგან": 1650,
2149
+ "მანგა": 1651,
2150
+ "უკა": 1652,
2151
+ "სიკა": 1653,
2152
+ "ლუმ": 1654,
2153
+ "ნაყე": 1655,
2154
+ "ტჰეტჰე": 1656,
2155
+ "ცედო": 1657,
2156
+ "ცინგა": 1658,
2157
+ "ფუმანეკა": 1659,
2158
+ "Ⴓკუ": 1660,
2159
+ "მფო": 1661,
2160
+ "წაკჰე": 1662,
2161
+ "ბუსო": 1663,
2162
+ "ქაკუ": 1664,
2163
+ "ფუტსჰანე": 1665,
2164
+ "ცალუ": 1666,
2165
+ "უკუნქ": 1667,
2166
+ "სელ": 1668,
2167
+ "კუზო": 1669,
2168
+ "ლწანა": 1670,
2169
+ "ფიკ": 1671,
2170
+ "ქჰუბე": 1672,
2171
+ "ხელელა": 1673,
2172
+ "ჯა": 1674,
2173
+ "ლამა": 1675,
2174
+ "ზაზი": 1676,
2175
+ "ლილეყო": 1677,
2176
+ "ინტეტჰო": 1678,
2177
+ "ჰლან": 1679,
2178
+ "პალა": 1680,
2179
+ "19": 1681,
2180
+ "წომ": 1682,
2181
+ "ხუ": 1683,
2182
+ "კწენზეკ��": 1684,
2183
+ "პჰულო": 1685,
2184
+ "ნდლელა": 1686,
2185
+ "ცჰუ": 1687,
2186
+ "კულა": 1688,
2187
+ "კუყე": 1689
2188
+ },
2189
+ "merges": [
2190
+ "t h",
2191
+ "i n",
2192
+ "th e",
2193
+ "a n",
2194
+ "e r",
2195
+ "o u",
2196
+ "r e",
2197
+ "o n",
2198
+ "a t",
2199
+ "e d",
2200
+ "e n",
2201
+ "t o",
2202
+ "in g",
2203
+ "an d",
2204
+ "i s",
2205
+ "a s",
2206
+ "a l",
2207
+ "o r",
2208
+ "o f",
2209
+ "a r",
2210
+ "i t",
2211
+ "e s",
2212
+ "h e",
2213
+ "s t",
2214
+ "l e",
2215
+ "o m",
2216
+ "s e",
2217
+ "b e",
2218
+ "a d",
2219
+ "o w",
2220
+ "l y",
2221
+ "c h",
2222
+ "w h",
2223
+ "th at",
2224
+ "y ou",
2225
+ "l i",
2226
+ "v e",
2227
+ "a c",
2228
+ "t i",
2229
+ "l d",
2230
+ "m e",
2231
+ "w as",
2232
+ "g h",
2233
+ "i d",
2234
+ "l l",
2235
+ "w i",
2236
+ "en t",
2237
+ "f or",
2238
+ "a y",
2239
+ "r o",
2240
+ "v er",
2241
+ "i c",
2242
+ "h er",
2243
+ "k e",
2244
+ "h is",
2245
+ "n o",
2246
+ "u t",
2247
+ "u n",
2248
+ "i r",
2249
+ "l o",
2250
+ "w e",
2251
+ "r i",
2252
+ "h a",
2253
+ "wi th",
2254
+ "gh t",
2255
+ "ou t",
2256
+ "i m",
2257
+ "i on",
2258
+ "al l",
2259
+ "a b",
2260
+ "on e",
2261
+ "n e",
2262
+ "g e",
2263
+ "ou ld",
2264
+ "t er",
2265
+ "m o",
2266
+ "h ad",
2267
+ "c e",
2268
+ "s he",
2269
+ "g o",
2270
+ "s h",
2271
+ "u r",
2272
+ "a m",
2273
+ "s o",
2274
+ "p e",
2275
+ "m y",
2276
+ "d e",
2277
+ "a re",
2278
+ "b ut",
2279
+ "om e",
2280
+ "f r",
2281
+ "the r",
2282
+ "f e",
2283
+ "s u",
2284
+ "d o",
2285
+ "c on",
2286
+ "t e",
2287
+ "a in",
2288
+ "er e",
2289
+ "p o",
2290
+ "i f",
2291
+ "the y",
2292
+ "u s",
2293
+ "a g",
2294
+ "t r",
2295
+ "n ow",
2296
+ "ou n",
2297
+ "th is",
2298
+ "ha ve",
2299
+ "no t",
2300
+ "s a",
2301
+ "i l",
2302
+ "u p",
2303
+ "th ing",
2304
+ "fr om",
2305
+ "a p",
2306
+ "h im",
2307
+ "ac k",
2308
+ "at ion",
2309
+ "an t",
2310
+ "ou r",
2311
+ "o p",
2312
+ "li ke",
2313
+ "u st",
2314
+ "es s",
2315
+ "b o",
2316
+ "o k",
2317
+ "u l",
2318
+ "in d",
2319
+ "e x",
2320
+ "c om",
2321
+ "s ome",
2322
+ "the re",
2323
+ "er s",
2324
+ "c o",
2325
+ "re s",
2326
+ "m an",
2327
+ "ar d",
2328
+ "p l",
2329
+ "w or",
2330
+ "w ay",
2331
+ "ti on",
2332
+ "f o",
2333
+ "c a",
2334
+ "w ere",
2335
+ "b y",
2336
+ "at e",
2337
+ "p ro",
2338
+ "t ed",
2339
+ "oun d",
2340
+ "ow n",
2341
+ "w ould",
2342
+ "t s",
2343
+ "wh at",
2344
+ "q u",
2345
+ "al ly",
2346
+ "i ght",
2347
+ "c k",
2348
+ "g r",
2349
+ "wh en",
2350
+ "v en",
2351
+ "c an",
2352
+ "ou gh",
2353
+ "in e",
2354
+ "en d",
2355
+ "p er",
2356
+ "ou s",
2357
+ "o d",
2358
+ "id e",
2359
+ "k now",
2360
+ "t y",
2361
+ "ver y",
2362
+ "s i",
2363
+ "a k",
2364
+ "wh o",
2365
+ "ab out",
2366
+ "i ll",
2367
+ "the m",
2368
+ "es t",
2369
+ "re d",
2370
+ "y e",
2371
+ "c ould",
2372
+ "on g",
2373
+ "you r",
2374
+ "the ir",
2375
+ "e m",
2376
+ "j ust",
2377
+ "o ther",
2378
+ "in to",
2379
+ "an y",
2380
+ "wh i",
2381
+ "u m",
2382
+ "t w",
2383
+ "as t",
2384
+ "d er",
2385
+ "d id",
2386
+ "i e",
2387
+ "be en",
2388
+ "ac e",
2389
+ "in k",
2390
+ "it y",
2391
+ "b ack",
2392
+ "t ing",
2393
+ "b r",
2394
+ "mo re",
2395
+ "a ke",
2396
+ "p p",
2397
+ "the n",
2398
+ "s p",
2399
+ "e l",
2400
+ "u se",
2401
+ "b l",
2402
+ "sa id",
2403
+ "o ver",
2404
+ "ge t",
2405
+ "ɑ ː",
2406
+ "i ː",
2407
+ "u ː",
2408
+ "ɜ ː",
2409
+ "ɔ ː",
2410
+ "o ː",
2411
+ "e ɪ",
2412
+ "o ʊ",
2413
+ "a ɪ",
2414
+ "a ʊ",
2415
+ "ɔ ɪ",
2416
+ "d ʒ",
2417
+ "t ʃ",
2418
+ "ɪ ŋ",
2419
+ "ᵻ d",
2420
+ "ˈ iː",
2421
+ "ˌ iː",
2422
+ "ˈ ɪ",
2423
+ "ˌ ɪ",
2424
+ "ˈ eɪ",
2425
+ "ˌ eɪ",
2426
+ "ˈ ɛ",
2427
+ "ˌ ɛ",
2428
+ "ˈ æ",
2429
+ "ˌ æ",
2430
+ "ˈ ɑː",
2431
+ "ˌ ɑː",
2432
+ "ˈ ɔː",
2433
+ "ˌ ɔː",
2434
+ "oː ɹ",
2435
+ "ˈ oːɹ",
2436
+ "ˌ oːɹ",
2437
+ "ˈ oʊ",
2438
+ "ˌ oʊ",
2439
+ "ˈ ʊ",
2440
+ "ˌ ʊ",
2441
+ "ˈ uː",
2442
+ "ˌ uː",
2443
+ "ˈ ɜː",
2444
+ "ˌ ɜː",
2445
+ "ˈ ʌ",
2446
+ "ˌ ʌ",
2447
+ "ˈ aɪ",
2448
+ "ˌ aɪ",
2449
+ "ˈ aʊ",
2450
+ "ˌ aʊ",
2451
+ "ˈ ɔɪ",
2452
+ "ˌ ɔɪ",
2453
+ "ˈ ɚ",
2454
+ "ˌ ɐ"
2455
+ ],
2456
+ "language": "xh"
2457
+ }
2458
+ }
multi/expanded_chatterbox_model/ve.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0921cab452fa278bc25cd23ffd59d36f816d7dc5181dd1bef9751a7fb61f63c
3
+ size 5695784
pt/Chatterbox-TTS-Portuguese/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
pt/Chatterbox-TTS-Portuguese/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - AdrienB134/portuguese-tts
5
+ - freds0/BRSpeech-TTS
6
+ language:
7
+ - pt
8
+ metrics:
9
+ - accuracy
10
+ base_model:
11
+ - ResembleAI/chatterbox
12
+ pipeline_tag: text-to-speech
13
+ tags:
14
+ - voice
15
+ - tts
16
+ - pt
17
+ - pt-br
18
+ - portuguese
19
+ ---
20
+
21
+ <h1 style="font-size: 32px">Chatterbox TTS Portuguese</h1>
22
+
23
+ # Overview
24
+
25
+ - **This project is a finetuned version of the ResembleAI/Chatterbox model, extended to include support for the Portuguese language. Hosted on Hugging Face at FearL0rd/Chatterbox-TTS-Portuguese, this model enhances text-to-speech (TTS) capabilities for Portuguese, focusing on natural and accurate speech generation.**
26
+
27
+ # Features
28
+
29
+
30
+ - **Portuguese TTS Support: Optimized for generating high-quality Portuguese speech, including Brazilian and European variants.**
31
+ - **Multilingual Compatibility: Retains the original multilingual capabilities of ResembleAI/Chatterbox.**
32
+ - **High-Quality Audio Output: Finetuned for clear, natural-sounding Portuguese speech suitable for conversational AI, audiobooks, and more.**
33
+ - **Applications: Ideal for TTS applications, virtual assistants, and accessibility tools requiring Portuguese support.**
34
+
pt/Chatterbox-TTS-Portuguese/conds.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6552d70568833628ba019c6b03459e77fe71ca197d5c560cef9411bee9d87f4e
3
+ size 107374
pt/Chatterbox-TTS-Portuguese/s3gen.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeaa7890908fad1067121b8922b6d3dd6901f590fbeab419c500a4a6cda922cb
3
+ size 1056486308
pt/Chatterbox-TTS-Portuguese/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/FearL0rd/Chatterbox-TTS-Portuguese
pt/Chatterbox-TTS-Portuguese/t3_cfg.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cecd6ef6d5fd3aced2feeb9ed2553f803751a944fb66f04483d5127a4d36084
3
+ size 2129653744
pt/Chatterbox-TTS-Portuguese/tokenizer.json ADDED
@@ -0,0 +1,1435 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "special": true,
9
+ "content": "[STOP]",
10
+ "single_word": false,
11
+ "lstrip": false,
12
+ "rstrip": false,
13
+ "normalized": false
14
+ },
15
+ {
16
+ "id": 1,
17
+ "special": true,
18
+ "content": "[UNK]",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false
23
+ },
24
+ {
25
+ "id": 2,
26
+ "special": true,
27
+ "content": "[SPACE]",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false
32
+ },
33
+ {
34
+ "id": 255,
35
+ "special": true,
36
+ "content": "[START]",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false
41
+ },
42
+ {
43
+ "id": 604,
44
+ "content": "[UH]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 605,
53
+ "content": "[UM]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 606,
62
+ "content": "[giggle]",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 607,
71
+ "content": "[laughter]",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 608,
80
+ "content": "[guffaw]",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 609,
89
+ "content": "[inhale]",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 610,
98
+ "content": "[exhale]",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 611,
107
+ "content": "[sigh]",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 612,
116
+ "content": "[cry]",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 613,
125
+ "content": "[bark]",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 614,
134
+ "content": "[howl]",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 615,
143
+ "content": "[meow]",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 616,
152
+ "content": "[singing]",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 617,
161
+ "content": "[music]",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 618,
170
+ "content": "[whistle]",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 619,
179
+ "content": "[humming]",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 620,
188
+ "content": "[gasp]",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 621,
197
+ "content": "[groan]",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 622,
206
+ "content": "[whisper]",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 623,
215
+ "content": "[mumble]",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 624,
224
+ "content": "[sniff]",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 625,
233
+ "content": "[sneeze]",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 626,
242
+ "content": "[cough]",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 627,
251
+ "content": "[snore]",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 628,
260
+ "content": "[chew]",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 629,
269
+ "content": "[sip]",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 630,
278
+ "content": "[clear_throat]",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 631,
287
+ "content": "[kiss]",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 632,
296
+ "content": "[shhh]",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 633,
305
+ "content": "[gibberish]",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 634,
314
+ "content": "[fr]",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 635,
323
+ "content": "[es]",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 636,
332
+ "content": "[de]",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 637,
341
+ "content": "[it]",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 638,
350
+ "content": "[ipa]",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 639,
359
+ "content": "[end_of_label]",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 695,
368
+ "content": "[PLACEHOLDER55]",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 696,
377
+ "content": "[PLACEHOLDER56]",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 697,
386
+ "content": "[PLACEHOLDER57]",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 698,
395
+ "content": "[PLACEHOLDER58]",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 699,
404
+ "content": "[PLACEHOLDER59]",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 700,
413
+ "content": "[PLACEHOLDER60]",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 701,
422
+ "content": "[PLACEHOLDER61]",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 702,
431
+ "content": "[PLACEHOLDER62]",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 703,
440
+ "content": "[PLACEHOLDER63]",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ }
447
+ ],
448
+ "normalizer": null,
449
+ "pre_tokenizer": {
450
+ "type": "Whitespace"
451
+ },
452
+ "post_processor": null,
453
+ "decoder": null,
454
+ "model": {
455
+ "type": "BPE",
456
+ "dropout": null,
457
+ "unk_token": "[UNK]",
458
+ "continuing_subword_prefix": null,
459
+ "end_of_word_suffix": null,
460
+ "fuse_unk": false,
461
+ "vocab": {
462
+ "[STOP]": 0,
463
+ "[UNK]": 1,
464
+ "[SPACE]": 2,
465
+ "!": 3,
466
+ "'": 4,
467
+ "(": 5,
468
+ ")": 6,
469
+ ",": 7,
470
+ "-": 8,
471
+ ".": 9,
472
+ "/": 10,
473
+ ":": 11,
474
+ ";": 12,
475
+ "?": 13,
476
+ "a": 14,
477
+ "b": 15,
478
+ "c": 16,
479
+ "d": 17,
480
+ "e": 18,
481
+ "f": 19,
482
+ "g": 20,
483
+ "h": 21,
484
+ "i": 22,
485
+ "j": 23,
486
+ "k": 24,
487
+ "l": 25,
488
+ "m": 26,
489
+ "n": 27,
490
+ "o": 28,
491
+ "p": 29,
492
+ "q": 30,
493
+ "r": 31,
494
+ "s": 32,
495
+ "t": 33,
496
+ "u": 34,
497
+ "v": 35,
498
+ "w": 36,
499
+ "x": 37,
500
+ "y": 38,
501
+ "z": 39,
502
+ "th": 40,
503
+ "in": 41,
504
+ "the": 42,
505
+ "an": 43,
506
+ "er": 44,
507
+ "ou": 45,
508
+ "re": 46,
509
+ "on": 47,
510
+ "at": 48,
511
+ "ed": 49,
512
+ "en": 50,
513
+ "to": 51,
514
+ "ing": 52,
515
+ "and": 53,
516
+ "is": 54,
517
+ "as": 55,
518
+ "al": 56,
519
+ "or": 57,
520
+ "of": 58,
521
+ "ar": 59,
522
+ "it": 60,
523
+ "es": 61,
524
+ "he": 62,
525
+ "st": 63,
526
+ "le": 64,
527
+ "om": 65,
528
+ "se": 66,
529
+ "be": 67,
530
+ "ad": 68,
531
+ "ow": 69,
532
+ "ly": 70,
533
+ "ch": 71,
534
+ "wh": 72,
535
+ "that": 73,
536
+ "you": 74,
537
+ "li": 75,
538
+ "ve": 76,
539
+ "ac": 77,
540
+ "ti": 78,
541
+ "ld": 79,
542
+ "me": 80,
543
+ "was": 81,
544
+ "gh": 82,
545
+ "id": 83,
546
+ "ll": 84,
547
+ "wi": 85,
548
+ "ent": 86,
549
+ "for": 87,
550
+ "ay": 88,
551
+ "ro": 89,
552
+ "ver": 90,
553
+ "ic": 91,
554
+ "her": 92,
555
+ "ke": 93,
556
+ "his": 94,
557
+ "no": 95,
558
+ "ut": 96,
559
+ "un": 97,
560
+ "ir": 98,
561
+ "lo": 99,
562
+ "we": 100,
563
+ "ri": 101,
564
+ "ha": 102,
565
+ "with": 103,
566
+ "ght": 104,
567
+ "out": 105,
568
+ "im": 106,
569
+ "ion": 107,
570
+ "all": 108,
571
+ "ab": 109,
572
+ "one": 110,
573
+ "ne": 111,
574
+ "ge": 112,
575
+ "ould": 113,
576
+ "ter": 114,
577
+ "mo": 115,
578
+ "had": 116,
579
+ "ce": 117,
580
+ "she": 118,
581
+ "go": 119,
582
+ "sh": 120,
583
+ "ur": 121,
584
+ "am": 122,
585
+ "so": 123,
586
+ "pe": 124,
587
+ "my": 125,
588
+ "de": 126,
589
+ "are": 127,
590
+ "but": 128,
591
+ "ome": 129,
592
+ "fr": 130,
593
+ "ther": 131,
594
+ "fe": 132,
595
+ "su": 133,
596
+ "do": 134,
597
+ "con": 135,
598
+ "te": 136,
599
+ "ain": 137,
600
+ "ere": 138,
601
+ "po": 139,
602
+ "if": 140,
603
+ "they": 141,
604
+ "us": 142,
605
+ "ag": 143,
606
+ "tr": 144,
607
+ "now": 145,
608
+ "oun": 146,
609
+ "this": 147,
610
+ "have": 148,
611
+ "not": 149,
612
+ "sa": 150,
613
+ "il": 151,
614
+ "up": 152,
615
+ "thing": 153,
616
+ "from": 154,
617
+ "ap": 155,
618
+ "him": 156,
619
+ "ack": 157,
620
+ "ation": 158,
621
+ "ant": 159,
622
+ "our": 160,
623
+ "op": 161,
624
+ "like": 162,
625
+ "ust": 163,
626
+ "ess": 164,
627
+ "bo": 165,
628
+ "ok": 166,
629
+ "ul": 167,
630
+ "ind": 168,
631
+ "ex": 169,
632
+ "com": 170,
633
+ "some": 171,
634
+ "there": 172,
635
+ "ers": 173,
636
+ "co": 174,
637
+ "res": 175,
638
+ "man": 176,
639
+ "ard": 177,
640
+ "pl": 178,
641
+ "wor": 179,
642
+ "way": 180,
643
+ "tion": 181,
644
+ "fo": 182,
645
+ "ca": 183,
646
+ "were": 184,
647
+ "by": 185,
648
+ "ate": 186,
649
+ "pro": 187,
650
+ "ted": 188,
651
+ "ound": 189,
652
+ "own": 190,
653
+ "would": 191,
654
+ "ts": 192,
655
+ "what": 193,
656
+ "qu": 194,
657
+ "ally": 195,
658
+ "ight": 196,
659
+ "ck": 197,
660
+ "gr": 198,
661
+ "when": 199,
662
+ "ven": 200,
663
+ "can": 201,
664
+ "ough": 202,
665
+ "ine": 203,
666
+ "end": 204,
667
+ "per": 205,
668
+ "ous": 206,
669
+ "od": 207,
670
+ "ide": 208,
671
+ "know": 209,
672
+ "ty": 210,
673
+ "very": 211,
674
+ "si": 212,
675
+ "ak": 213,
676
+ "who": 214,
677
+ "about": 215,
678
+ "ill": 216,
679
+ "them": 217,
680
+ "est": 218,
681
+ "red": 219,
682
+ "ye": 220,
683
+ "could": 221,
684
+ "ong": 222,
685
+ "your": 223,
686
+ "their": 224,
687
+ "em": 225,
688
+ "just": 226,
689
+ "other": 227,
690
+ "into": 228,
691
+ "any": 229,
692
+ "whi": 230,
693
+ "um": 231,
694
+ "tw": 232,
695
+ "ast": 233,
696
+ "der": 234,
697
+ "did": 235,
698
+ "ie": 236,
699
+ "been": 237,
700
+ "ace": 238,
701
+ "ink": 239,
702
+ "ity": 240,
703
+ "back": 241,
704
+ "ting": 242,
705
+ "br": 243,
706
+ "more": 244,
707
+ "ake": 245,
708
+ "pp": 246,
709
+ "then": 247,
710
+ "sp": 248,
711
+ "el": 249,
712
+ "use": 250,
713
+ "bl": 251,
714
+ "said": 252,
715
+ "over": 253,
716
+ "get": 254,
717
+ "[START]": 255,
718
+ "\"": 256,
719
+ "#": 257,
720
+ "$": 258,
721
+ "%": 259,
722
+ "&": 260,
723
+ "*": 261,
724
+ "+": 262,
725
+ "0": 263,
726
+ "1": 264,
727
+ "2": 265,
728
+ "3": 266,
729
+ "4": 267,
730
+ "5": 268,
731
+ "6": 269,
732
+ "7": 270,
733
+ "8": 271,
734
+ "9": 272,
735
+ "<": 273,
736
+ "=": 274,
737
+ ">": 275,
738
+ "@": 276,
739
+ "A": 277,
740
+ "B": 278,
741
+ "C": 279,
742
+ "D": 280,
743
+ "E": 281,
744
+ "F": 282,
745
+ "G": 283,
746
+ "H": 284,
747
+ "I": 285,
748
+ "J": 286,
749
+ "K": 287,
750
+ "L": 288,
751
+ "M": 289,
752
+ "N": 290,
753
+ "O": 291,
754
+ "P": 292,
755
+ "Q": 293,
756
+ "R": 294,
757
+ "S": 295,
758
+ "T": 296,
759
+ "U": 297,
760
+ "V": 298,
761
+ "W": 299,
762
+ "X": 300,
763
+ "Y": 301,
764
+ "Z": 302,
765
+ "[": 303,
766
+ "\\": 304,
767
+ "]": 305,
768
+ "^": 306,
769
+ "_": 307,
770
+ "`": 308,
771
+ "{": 309,
772
+ "|": 310,
773
+ "}": 311,
774
+ "~": 312,
775
+ "‐": 313,
776
+ "‑": 314,
777
+ "‒": 315,
778
+ "–": 316,
779
+ "—": 317,
780
+ "―": 318,
781
+ "‖": 319,
782
+ "‗": 320,
783
+ "‘": 321,
784
+ "’": 322,
785
+ "‚": 323,
786
+ "‛": 324,
787
+ "“": 325,
788
+ "”": 326,
789
+ "„": 327,
790
+ "‟": 328,
791
+ " ": 329,
792
+ "¡": 330,
793
+ "¢": 331,
794
+ "£": 332,
795
+ "¤": 333,
796
+ "¥": 334,
797
+ "¦": 335,
798
+ "§": 336,
799
+ "¨": 337,
800
+ "©": 338,
801
+ "ª": 339,
802
+ "«": 340,
803
+ "¬": 341,
804
+ "­": 342,
805
+ "®": 343,
806
+ "¯": 344,
807
+ "°": 345,
808
+ "±": 346,
809
+ "²": 347,
810
+ "³": 348,
811
+ "´": 349,
812
+ "µ": 350,
813
+ "¶": 351,
814
+ "·": 352,
815
+ "¸": 353,
816
+ "¹": 354,
817
+ "º": 355,
818
+ "»": 356,
819
+ "¼": 357,
820
+ "½": 358,
821
+ "¾": 359,
822
+ "¿": 360,
823
+ "À": 361,
824
+ "Á": 362,
825
+ "Â": 363,
826
+ "Ã": 364,
827
+ "Ä": 365,
828
+ "Å": 366,
829
+ "Æ": 367,
830
+ "Ç": 368,
831
+ "È": 369,
832
+ "É": 370,
833
+ "Ê": 371,
834
+ "Ë": 372,
835
+ "Ì": 373,
836
+ "Í": 374,
837
+ "Î": 375,
838
+ "Ï": 376,
839
+ "Ð": 377,
840
+ "Ñ": 378,
841
+ "Ò": 379,
842
+ "Ó": 380,
843
+ "Ô": 381,
844
+ "Õ": 382,
845
+ "Ö": 383,
846
+ "×": 384,
847
+ "Ø": 385,
848
+ "Ù": 386,
849
+ "Ú": 387,
850
+ "Û": 388,
851
+ "Ü": 389,
852
+ "Ý": 390,
853
+ "Þ": 391,
854
+ "ß": 392,
855
+ "à": 393,
856
+ "á": 394,
857
+ "â": 395,
858
+ "ã": 396,
859
+ "ä": 397,
860
+ "å": 398,
861
+ "æ": 399,
862
+ "ç": 400,
863
+ "è": 401,
864
+ "é": 402,
865
+ "ê": 403,
866
+ "ë": 404,
867
+ "ì": 405,
868
+ "í": 406,
869
+ "î": 407,
870
+ "ï": 408,
871
+ "ð": 409,
872
+ "ñ": 410,
873
+ "ò": 411,
874
+ "ó": 412,
875
+ "ô": 413,
876
+ "õ": 414,
877
+ "ö": 415,
878
+ "÷": 416,
879
+ "ø": 417,
880
+ "ù": 418,
881
+ "ú": 419,
882
+ "û": 420,
883
+ "ü": 421,
884
+ "ý": 422,
885
+ "þ": 423,
886
+ "ÿ": 424,
887
+ "ɐ": 425,
888
+ "ɑ": 426,
889
+ "ɒ": 427,
890
+ "ɓ": 428,
891
+ "ɔ": 429,
892
+ "ɕ": 430,
893
+ "ɖ": 431,
894
+ "ɗ": 432,
895
+ "ɘ": 433,
896
+ "ə": 434,
897
+ "ɚ": 435,
898
+ "ɛ": 436,
899
+ "ɜ": 437,
900
+ "ɝ": 438,
901
+ "ɞ": 439,
902
+ "ɟ": 440,
903
+ "ɠ": 441,
904
+ "ɡ": 442,
905
+ "ɢ": 443,
906
+ "ɣ": 444,
907
+ "ɤ": 445,
908
+ "ɥ": 446,
909
+ "ɦ": 447,
910
+ "ɧ": 448,
911
+ "ɨ": 449,
912
+ "ɩ": 450,
913
+ "ɪ": 451,
914
+ "ɫ": 452,
915
+ "ɬ": 453,
916
+ "ɭ": 454,
917
+ "ɮ": 455,
918
+ "ɯ": 456,
919
+ "ɰ": 457,
920
+ "ɱ": 458,
921
+ "ɲ": 459,
922
+ "ɳ": 460,
923
+ "ɴ": 461,
924
+ "ɵ": 462,
925
+ "ɶ": 463,
926
+ "ɷ": 464,
927
+ "ɸ": 465,
928
+ "ɹ": 466,
929
+ "ɺ": 467,
930
+ "ɻ": 468,
931
+ "ɼ": 469,
932
+ "ɽ": 470,
933
+ "ɾ": 471,
934
+ "ɿ": 472,
935
+ "ʀ": 473,
936
+ "ʁ": 474,
937
+ "ʂ": 475,
938
+ "ʃ": 476,
939
+ "ʄ": 477,
940
+ "ʅ": 478,
941
+ "ʆ": 479,
942
+ "ʇ": 480,
943
+ "ʈ": 481,
944
+ "ʉ": 482,
945
+ "ʊ": 483,
946
+ "ʋ": 484,
947
+ "ʌ": 485,
948
+ "ʍ": 486,
949
+ "ʎ": 487,
950
+ "ʏ": 488,
951
+ "ʐ": 489,
952
+ "ʑ": 490,
953
+ "ʒ": 491,
954
+ "ʓ": 492,
955
+ "ʔ": 493,
956
+ "ʕ": 494,
957
+ "ʖ": 495,
958
+ "ʗ": 496,
959
+ "ʘ": 497,
960
+ "ʙ": 498,
961
+ "ʚ": 499,
962
+ "ʛ": 500,
963
+ "ʜ": 501,
964
+ "ʝ": 502,
965
+ "ʞ": 503,
966
+ "ʟ": 504,
967
+ "ʠ": 505,
968
+ "ʡ": 506,
969
+ "ʢ": 507,
970
+ "ʣ": 508,
971
+ "ʤ": 509,
972
+ "ʥ": 510,
973
+ "ʦ": 511,
974
+ "ʧ": 512,
975
+ "ʨ": 513,
976
+ "ʩ": 514,
977
+ "ʪ": 515,
978
+ "ʫ": 516,
979
+ "ʬ": 517,
980
+ "ʭ": 518,
981
+ "ʮ": 519,
982
+ "ʯ": 520,
983
+ "ʰ": 521,
984
+ "ʱ": 522,
985
+ "ʲ": 523,
986
+ "ʳ": 524,
987
+ "ʴ": 525,
988
+ "ʵ": 526,
989
+ "ʶ": 527,
990
+ "ʷ": 528,
991
+ "ʸ": 529,
992
+ "ʹ": 530,
993
+ "ʺ": 531,
994
+ "ʻ": 532,
995
+ "ʼ": 533,
996
+ "ʽ": 534,
997
+ "ʾ": 535,
998
+ "ʿ": 536,
999
+ "ˀ": 537,
1000
+ "ˁ": 538,
1001
+ "˂": 539,
1002
+ "˃": 540,
1003
+ "˄": 541,
1004
+ "˅": 542,
1005
+ "ˆ": 543,
1006
+ "ˇ": 544,
1007
+ "ˈ": 545,
1008
+ "ˉ": 546,
1009
+ "ˊ": 547,
1010
+ "ˋ": 548,
1011
+ "ˌ": 549,
1012
+ "ˍ": 550,
1013
+ "ˎ": 551,
1014
+ "ˏ": 552,
1015
+ "ː": 553,
1016
+ "ˑ": 554,
1017
+ "˒": 555,
1018
+ "˓": 556,
1019
+ "˔": 557,
1020
+ "˕": 558,
1021
+ "˖": 559,
1022
+ "˗": 560,
1023
+ "˘": 561,
1024
+ "˙": 562,
1025
+ "˚": 563,
1026
+ "˛": 564,
1027
+ "˜": 565,
1028
+ "˝": 566,
1029
+ "˞": 567,
1030
+ "˟": 568,
1031
+ "ˠ": 569,
1032
+ "ˡ": 570,
1033
+ "ˢ": 571,
1034
+ "ˣ": 572,
1035
+ "ˤ": 573,
1036
+ "˥": 574,
1037
+ "˦": 575,
1038
+ "˧": 576,
1039
+ "˨": 577,
1040
+ "˩": 578,
1041
+ "˪": 579,
1042
+ "˫": 580,
1043
+ "ˬ": 581,
1044
+ "˭": 582,
1045
+ "ˮ": 583,
1046
+ "˯": 584,
1047
+ "˰": 585,
1048
+ "˱": 586,
1049
+ "˲": 587,
1050
+ "˳": 588,
1051
+ "˴": 589,
1052
+ "˵": 590,
1053
+ "˶": 591,
1054
+ "˷": 592,
1055
+ "˸": 593,
1056
+ "˹": 594,
1057
+ "˺": 595,
1058
+ "˻": 596,
1059
+ "˼": 597,
1060
+ "˽": 598,
1061
+ "˾": 599,
1062
+ "˿": 600,
1063
+ "ā": 601,
1064
+ "ō": 602,
1065
+ "…": 603,
1066
+ "[UH]": 604,
1067
+ "[UM]": 605,
1068
+ "[giggle]": 606,
1069
+ "[laughter]": 607,
1070
+ "[guffaw]": 608,
1071
+ "[inhale]": 609,
1072
+ "[exhale]": 610,
1073
+ "[sigh]": 611,
1074
+ "[cry]": 612,
1075
+ "[bark]": 613,
1076
+ "[howl]": 614,
1077
+ "[meow]": 615,
1078
+ "[singing]": 616,
1079
+ "[music]": 617,
1080
+ "[whistle]": 618,
1081
+ "[humming]": 619,
1082
+ "[gasp]": 620,
1083
+ "[groan]": 621,
1084
+ "[whisper]": 622,
1085
+ "[mumble]": 623,
1086
+ "[sniff]": 624,
1087
+ "[sneeze]": 625,
1088
+ "[cough]": 626,
1089
+ "[snore]": 627,
1090
+ "[chew]": 628,
1091
+ "[sip]": 629,
1092
+ "[clear_throat]": 630,
1093
+ "[kiss]": 631,
1094
+ "[shhh]": 632,
1095
+ "[gibberish]": 633,
1096
+ "[fr]": 634,
1097
+ "[es]": 635,
1098
+ "[de]": 636,
1099
+ "[it]": 637,
1100
+ "[ipa]": 638,
1101
+ "[end_of_label]": 639,
1102
+ "ŋ": 640,
1103
+ "ᵻ": 641,
1104
+ "θ": 642,
1105
+ "̩": 643,
1106
+ "\u0303": 644,
1107
+ "ɑː": 645,
1108
+ "iː": 646,
1109
+ "uː": 647,
1110
+ "ɜː": 648,
1111
+ "ɔː": 649,
1112
+ "oː": 650,
1113
+ "eɪ": 651,
1114
+ "oʊ": 652,
1115
+ "aɪ": 653,
1116
+ "aʊ": 654,
1117
+ "ɔɪ": 655,
1118
+ "dʒ": 656,
1119
+ "tʃ": 657,
1120
+ "ɪŋ": 658,
1121
+ "ᵻd": 659,
1122
+ "ˈiː": 660,
1123
+ "ˌiː": 661,
1124
+ "ˈɪ": 662,
1125
+ "ˌɪ": 663,
1126
+ "ˈeɪ": 664,
1127
+ "ˌeɪ": 665,
1128
+ "ˈɛ": 666,
1129
+ "ˌɛ": 667,
1130
+ "ˈæ": 668,
1131
+ "ˌæ": 669,
1132
+ "ˈɑː": 670,
1133
+ "ˌɑː": 671,
1134
+ "ˈɔː": 672,
1135
+ "ˌɔː": 673,
1136
+ "oːɹ": 674,
1137
+ "ˈoːɹ": 675,
1138
+ "ˌoːɹ": 676,
1139
+ "ˈoʊ": 677,
1140
+ "ˌoʊ": 678,
1141
+ "ˈʊ": 679,
1142
+ "ˌʊ": 680,
1143
+ "ˈuː": 681,
1144
+ "ˌuː": 682,
1145
+ "ˈɜː": 683,
1146
+ "ˌɜː": 684,
1147
+ "ˈʌ": 685,
1148
+ "ˌʌ": 686,
1149
+ "ˈaɪ": 687,
1150
+ "ˌaɪ": 688,
1151
+ "ˈaʊ": 689,
1152
+ "ˌaʊ": 690,
1153
+ "ˈɔɪ": 691,
1154
+ "ˌɔɪ": 692,
1155
+ "ˈɚ": 693,
1156
+ "ˌɐ": 694,
1157
+ "[PLACEHOLDER55]": 695,
1158
+ "[PLACEHOLDER56]": 696,
1159
+ "[PLACEHOLDER57]": 697,
1160
+ "[PLACEHOLDER58]": 698,
1161
+ "[PLACEHOLDER59]": 699,
1162
+ "[PLACEHOLDER60]": 700,
1163
+ "[PLACEHOLDER61]": 701,
1164
+ "[PLACEHOLDER62]": 702,
1165
+ "[PLACEHOLDER63]": 703
1166
+ },
1167
+ "merges": [
1168
+ "t h",
1169
+ "i n",
1170
+ "th e",
1171
+ "a n",
1172
+ "e r",
1173
+ "o u",
1174
+ "r e",
1175
+ "o n",
1176
+ "a t",
1177
+ "e d",
1178
+ "e n",
1179
+ "t o",
1180
+ "in g",
1181
+ "an d",
1182
+ "i s",
1183
+ "a s",
1184
+ "a l",
1185
+ "o r",
1186
+ "o f",
1187
+ "a r",
1188
+ "i t",
1189
+ "e s",
1190
+ "h e",
1191
+ "s t",
1192
+ "l e",
1193
+ "o m",
1194
+ "s e",
1195
+ "b e",
1196
+ "a d",
1197
+ "o w",
1198
+ "l y",
1199
+ "c h",
1200
+ "w h",
1201
+ "th at",
1202
+ "y ou",
1203
+ "l i",
1204
+ "v e",
1205
+ "a c",
1206
+ "t i",
1207
+ "l d",
1208
+ "m e",
1209
+ "w as",
1210
+ "g h",
1211
+ "i d",
1212
+ "l l",
1213
+ "w i",
1214
+ "en t",
1215
+ "f or",
1216
+ "a y",
1217
+ "r o",
1218
+ "v er",
1219
+ "i c",
1220
+ "h er",
1221
+ "k e",
1222
+ "h is",
1223
+ "n o",
1224
+ "u t",
1225
+ "u n",
1226
+ "i r",
1227
+ "l o",
1228
+ "w e",
1229
+ "r i",
1230
+ "h a",
1231
+ "wi th",
1232
+ "gh t",
1233
+ "ou t",
1234
+ "i m",
1235
+ "i on",
1236
+ "al l",
1237
+ "a b",
1238
+ "on e",
1239
+ "n e",
1240
+ "g e",
1241
+ "ou ld",
1242
+ "t er",
1243
+ "m o",
1244
+ "h ad",
1245
+ "c e",
1246
+ "s he",
1247
+ "g o",
1248
+ "s h",
1249
+ "u r",
1250
+ "a m",
1251
+ "s o",
1252
+ "p e",
1253
+ "m y",
1254
+ "d e",
1255
+ "a re",
1256
+ "b ut",
1257
+ "om e",
1258
+ "f r",
1259
+ "the r",
1260
+ "f e",
1261
+ "s u",
1262
+ "d o",
1263
+ "c on",
1264
+ "t e",
1265
+ "a in",
1266
+ "er e",
1267
+ "p o",
1268
+ "i f",
1269
+ "the y",
1270
+ "u s",
1271
+ "a g",
1272
+ "t r",
1273
+ "n ow",
1274
+ "ou n",
1275
+ "th is",
1276
+ "ha ve",
1277
+ "no t",
1278
+ "s a",
1279
+ "i l",
1280
+ "u p",
1281
+ "th ing",
1282
+ "fr om",
1283
+ "a p",
1284
+ "h im",
1285
+ "ac k",
1286
+ "at ion",
1287
+ "an t",
1288
+ "ou r",
1289
+ "o p",
1290
+ "li ke",
1291
+ "u st",
1292
+ "es s",
1293
+ "b o",
1294
+ "o k",
1295
+ "u l",
1296
+ "in d",
1297
+ "e x",
1298
+ "c om",
1299
+ "s ome",
1300
+ "the re",
1301
+ "er s",
1302
+ "c o",
1303
+ "re s",
1304
+ "m an",
1305
+ "ar d",
1306
+ "p l",
1307
+ "w or",
1308
+ "w ay",
1309
+ "ti on",
1310
+ "f o",
1311
+ "c a",
1312
+ "w ere",
1313
+ "b y",
1314
+ "at e",
1315
+ "p ro",
1316
+ "t ed",
1317
+ "oun d",
1318
+ "ow n",
1319
+ "w ould",
1320
+ "t s",
1321
+ "wh at",
1322
+ "q u",
1323
+ "al ly",
1324
+ "i ght",
1325
+ "c k",
1326
+ "g r",
1327
+ "wh en",
1328
+ "v en",
1329
+ "c an",
1330
+ "ou gh",
1331
+ "in e",
1332
+ "en d",
1333
+ "p er",
1334
+ "ou s",
1335
+ "o d",
1336
+ "id e",
1337
+ "k now",
1338
+ "t y",
1339
+ "ver y",
1340
+ "s i",
1341
+ "a k",
1342
+ "wh o",
1343
+ "ab out",
1344
+ "i ll",
1345
+ "the m",
1346
+ "es t",
1347
+ "re d",
1348
+ "y e",
1349
+ "c ould",
1350
+ "on g",
1351
+ "you r",
1352
+ "the ir",
1353
+ "e m",
1354
+ "j ust",
1355
+ "o ther",
1356
+ "in to",
1357
+ "an y",
1358
+ "wh i",
1359
+ "u m",
1360
+ "t w",
1361
+ "as t",
1362
+ "d er",
1363
+ "d id",
1364
+ "i e",
1365
+ "be en",
1366
+ "ac e",
1367
+ "in k",
1368
+ "it y",
1369
+ "b ack",
1370
+ "t ing",
1371
+ "b r",
1372
+ "mo re",
1373
+ "a ke",
1374
+ "p p",
1375
+ "the n",
1376
+ "s p",
1377
+ "e l",
1378
+ "u se",
1379
+ "b l",
1380
+ "sa id",
1381
+ "o ver",
1382
+ "ge t",
1383
+ "ɑ ː",
1384
+ "i ː",
1385
+ "u ː",
1386
+ "ɜ ː",
1387
+ "ɔ ː",
1388
+ "o ː",
1389
+ "e ɪ",
1390
+ "o ʊ",
1391
+ "a ɪ",
1392
+ "a ʊ",
1393
+ "ɔ ɪ",
1394
+ "d ʒ",
1395
+ "t ʃ",
1396
+ "ɪ ŋ",
1397
+ "ᵻ d",
1398
+ "ˈ iː",
1399
+ "ˌ iː",
1400
+ "ˈ ɪ",
1401
+ "ˌ ɪ",
1402
+ "ˈ eɪ",
1403
+ "ˌ eɪ",
1404
+ "ˈ ɛ",
1405
+ "ˌ ɛ",
1406
+ "ˈ æ",
1407
+ "ˌ æ",
1408
+ "ˈ ɑː",
1409
+ "ˌ ɑː",
1410
+ "ˈ ɔː",
1411
+ "ˌ ɔː",
1412
+ "oː ɹ",
1413
+ "ˈ oːɹ",
1414
+ "ˌ oːɹ",
1415
+ "ˈ oʊ",
1416
+ "ˌ oʊ",
1417
+ "ˈ ʊ",
1418
+ "ˌ ʊ",
1419
+ "ˈ uː",
1420
+ "ˌ uː",
1421
+ "ˈ ɜː",
1422
+ "ˌ ɜː",
1423
+ "ˈ ʌ",
1424
+ "ˌ ʌ",
1425
+ "ˈ aɪ",
1426
+ "ˌ aɪ",
1427
+ "ˈ aʊ",
1428
+ "ˌ aʊ",
1429
+ "ˈ ɔɪ",
1430
+ "ˌ ɔɪ",
1431
+ "ˈ ɚ",
1432
+ "ˌ ɐ"
1433
+ ]
1434
+ }
1435
+ }
pt/Chatterbox-TTS-Portuguese/ve.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0921cab452fa278bc25cd23ffd59d36f816d7dc5181dd1bef9751a7fb61f63c
3
+ size 5695784
ru/Chatterbox-Russian-TTS/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
ru/Chatterbox-Russian-TTS/source.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/zAnonymousWizard/Chatterbox-Russian-TTS
ru/Chatterbox-Russian-TTS/t3_cfg_16000_steps.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762f8e20e2605f806ac6e7706ba37cb98b6f5281eebc76b10b12136cb1a0016e
3
+ size 2132112248
ru/Chatterbox-Russian-TTS/tokenizer.json ADDED
@@ -0,0 +1,1735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "special": true,
9
+ "content": "[STOP]",
10
+ "single_word": false,
11
+ "lstrip": false,
12
+ "rstrip": false,
13
+ "normalized": false
14
+ },
15
+ {
16
+ "id": 1,
17
+ "special": true,
18
+ "content": "[UNK]",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false
23
+ },
24
+ {
25
+ "id": 2,
26
+ "special": true,
27
+ "content": "[SPACE]",
28
+ "single_word": false,
29
+ "lstrip": false,
30
+ "rstrip": false,
31
+ "normalized": false
32
+ },
33
+ {
34
+ "id": 255,
35
+ "special": true,
36
+ "content": "[START]",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false
41
+ },
42
+ {
43
+ "id": 604,
44
+ "content": "[UH]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 605,
53
+ "content": "[UM]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 606,
62
+ "content": "[giggle]",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 607,
71
+ "content": "[laughter]",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 608,
80
+ "content": "[guffaw]",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 609,
89
+ "content": "[inhale]",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 610,
98
+ "content": "[exhale]",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 611,
107
+ "content": "[sigh]",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 612,
116
+ "content": "[cry]",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 613,
125
+ "content": "[bark]",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 614,
134
+ "content": "[howl]",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 615,
143
+ "content": "[meow]",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 616,
152
+ "content": "[singing]",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 617,
161
+ "content": "[music]",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 618,
170
+ "content": "[whistle]",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 619,
179
+ "content": "[humming]",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 620,
188
+ "content": "[gasp]",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 621,
197
+ "content": "[groan]",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 622,
206
+ "content": "[whisper]",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 623,
215
+ "content": "[mumble]",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 624,
224
+ "content": "[sniff]",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 625,
233
+ "content": "[sneeze]",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 626,
242
+ "content": "[cough]",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 627,
251
+ "content": "[snore]",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 628,
260
+ "content": "[chew]",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 629,
269
+ "content": "[sip]",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 630,
278
+ "content": "[clear_throat]",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 631,
287
+ "content": "[kiss]",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 632,
296
+ "content": "[shhh]",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 633,
305
+ "content": "[gibberish]",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 634,
314
+ "content": "[fr]",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 635,
323
+ "content": "[es]",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 636,
332
+ "content": "[de]",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 637,
341
+ "content": "[it]",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 638,
350
+ "content": "[ipa]",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 639,
359
+ "content": "[end_of_label]",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 695,
368
+ "content": "[PLACEHOLDER55]",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 696,
377
+ "content": "[PLACEHOLDER56]",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 697,
386
+ "content": "[PLACEHOLDER57]",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 698,
395
+ "content": "[PLACEHOLDER58]",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 699,
404
+ "content": "[PLACEHOLDER59]",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 700,
413
+ "content": "[PLACEHOLDER60]",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 701,
422
+ "content": "[PLACEHOLDER61]",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 702,
431
+ "content": "[PLACEHOLDER62]",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 703,
440
+ "content": "[PLACEHOLDER63]",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ }
447
+ ],
448
+ "normalizer": null,
449
+ "pre_tokenizer": {
450
+ "type": "Whitespace"
451
+ },
452
+ "post_processor": null,
453
+ "decoder": null,
454
+ "model": {
455
+ "type": "BPE",
456
+ "dropout": null,
457
+ "unk_token": "[UNK]",
458
+ "continuing_subword_prefix": null,
459
+ "end_of_word_suffix": null,
460
+ "fuse_unk": false,
461
+ "vocab": {
462
+ "[STOP]": 0,
463
+ "[UNK]": 1,
464
+ "[SPACE]": 2,
465
+ "!": 3,
466
+ "'": 4,
467
+ "(": 5,
468
+ ")": 6,
469
+ ",": 7,
470
+ "-": 8,
471
+ ".": 9,
472
+ "/": 10,
473
+ ":": 11,
474
+ ";": 12,
475
+ "?": 13,
476
+ "a": 14,
477
+ "b": 15,
478
+ "c": 16,
479
+ "d": 17,
480
+ "e": 18,
481
+ "f": 19,
482
+ "g": 20,
483
+ "h": 21,
484
+ "i": 22,
485
+ "j": 23,
486
+ "k": 24,
487
+ "l": 25,
488
+ "m": 26,
489
+ "n": 27,
490
+ "o": 28,
491
+ "p": 29,
492
+ "q": 30,
493
+ "r": 31,
494
+ "s": 32,
495
+ "t": 33,
496
+ "u": 34,
497
+ "v": 35,
498
+ "w": 36,
499
+ "x": 37,
500
+ "y": 38,
501
+ "z": 39,
502
+ "th": 40,
503
+ "in": 41,
504
+ "the": 42,
505
+ "an": 43,
506
+ "er": 44,
507
+ "ou": 45,
508
+ "re": 46,
509
+ "on": 47,
510
+ "at": 48,
511
+ "ed": 49,
512
+ "en": 50,
513
+ "to": 51,
514
+ "ing": 52,
515
+ "and": 53,
516
+ "is": 54,
517
+ "as": 55,
518
+ "al": 56,
519
+ "or": 57,
520
+ "of": 58,
521
+ "ar": 59,
522
+ "it": 60,
523
+ "es": 61,
524
+ "he": 62,
525
+ "st": 63,
526
+ "le": 64,
527
+ "om": 65,
528
+ "se": 66,
529
+ "be": 67,
530
+ "ad": 68,
531
+ "ow": 69,
532
+ "ly": 70,
533
+ "ch": 71,
534
+ "wh": 72,
535
+ "that": 73,
536
+ "you": 74,
537
+ "li": 75,
538
+ "ve": 76,
539
+ "ac": 77,
540
+ "ti": 78,
541
+ "ld": 79,
542
+ "me": 80,
543
+ "was": 81,
544
+ "gh": 82,
545
+ "id": 83,
546
+ "ll": 84,
547
+ "wi": 85,
548
+ "ent": 86,
549
+ "for": 87,
550
+ "ay": 88,
551
+ "ro": 89,
552
+ "ver": 90,
553
+ "ic": 91,
554
+ "her": 92,
555
+ "ke": 93,
556
+ "his": 94,
557
+ "no": 95,
558
+ "ut": 96,
559
+ "un": 97,
560
+ "ir": 98,
561
+ "lo": 99,
562
+ "we": 100,
563
+ "ri": 101,
564
+ "ha": 102,
565
+ "with": 103,
566
+ "ght": 104,
567
+ "out": 105,
568
+ "im": 106,
569
+ "ion": 107,
570
+ "all": 108,
571
+ "ab": 109,
572
+ "one": 110,
573
+ "ne": 111,
574
+ "ge": 112,
575
+ "ould": 113,
576
+ "ter": 114,
577
+ "mo": 115,
578
+ "had": 116,
579
+ "ce": 117,
580
+ "she": 118,
581
+ "go": 119,
582
+ "sh": 120,
583
+ "ur": 121,
584
+ "am": 122,
585
+ "so": 123,
586
+ "pe": 124,
587
+ "my": 125,
588
+ "de": 126,
589
+ "are": 127,
590
+ "but": 128,
591
+ "ome": 129,
592
+ "fr": 130,
593
+ "ther": 131,
594
+ "fe": 132,
595
+ "su": 133,
596
+ "do": 134,
597
+ "con": 135,
598
+ "te": 136,
599
+ "ain": 137,
600
+ "ere": 138,
601
+ "po": 139,
602
+ "if": 140,
603
+ "they": 141,
604
+ "us": 142,
605
+ "ag": 143,
606
+ "tr": 144,
607
+ "now": 145,
608
+ "oun": 146,
609
+ "this": 147,
610
+ "have": 148,
611
+ "not": 149,
612
+ "sa": 150,
613
+ "il": 151,
614
+ "up": 152,
615
+ "thing": 153,
616
+ "from": 154,
617
+ "ap": 155,
618
+ "him": 156,
619
+ "ack": 157,
620
+ "ation": 158,
621
+ "ant": 159,
622
+ "our": 160,
623
+ "op": 161,
624
+ "like": 162,
625
+ "ust": 163,
626
+ "ess": 164,
627
+ "bo": 165,
628
+ "ok": 166,
629
+ "ul": 167,
630
+ "ind": 168,
631
+ "ex": 169,
632
+ "com": 170,
633
+ "some": 171,
634
+ "there": 172,
635
+ "ers": 173,
636
+ "co": 174,
637
+ "res": 175,
638
+ "man": 176,
639
+ "ard": 177,
640
+ "pl": 178,
641
+ "wor": 179,
642
+ "way": 180,
643
+ "tion": 181,
644
+ "fo": 182,
645
+ "ca": 183,
646
+ "were": 184,
647
+ "by": 185,
648
+ "ate": 186,
649
+ "pro": 187,
650
+ "ted": 188,
651
+ "ound": 189,
652
+ "own": 190,
653
+ "would": 191,
654
+ "ts": 192,
655
+ "what": 193,
656
+ "qu": 194,
657
+ "ally": 195,
658
+ "ight": 196,
659
+ "ck": 197,
660
+ "gr": 198,
661
+ "when": 199,
662
+ "ven": 200,
663
+ "can": 201,
664
+ "ough": 202,
665
+ "ine": 203,
666
+ "end": 204,
667
+ "per": 205,
668
+ "ous": 206,
669
+ "od": 207,
670
+ "ide": 208,
671
+ "know": 209,
672
+ "ty": 210,
673
+ "very": 211,
674
+ "si": 212,
675
+ "ak": 213,
676
+ "who": 214,
677
+ "about": 215,
678
+ "ill": 216,
679
+ "them": 217,
680
+ "est": 218,
681
+ "red": 219,
682
+ "ye": 220,
683
+ "could": 221,
684
+ "ong": 222,
685
+ "your": 223,
686
+ "their": 224,
687
+ "em": 225,
688
+ "just": 226,
689
+ "other": 227,
690
+ "into": 228,
691
+ "any": 229,
692
+ "whi": 230,
693
+ "um": 231,
694
+ "tw": 232,
695
+ "ast": 233,
696
+ "der": 234,
697
+ "did": 235,
698
+ "ie": 236,
699
+ "been": 237,
700
+ "ace": 238,
701
+ "ink": 239,
702
+ "ity": 240,
703
+ "back": 241,
704
+ "ting": 242,
705
+ "br": 243,
706
+ "more": 244,
707
+ "ake": 245,
708
+ "pp": 246,
709
+ "then": 247,
710
+ "sp": 248,
711
+ "el": 249,
712
+ "use": 250,
713
+ "bl": 251,
714
+ "said": 252,
715
+ "over": 253,
716
+ "get": 254,
717
+ "[START]": 255,
718
+ "\"": 256,
719
+ "#": 257,
720
+ "$": 258,
721
+ "%": 259,
722
+ "&": 260,
723
+ "*": 261,
724
+ "+": 262,
725
+ "0": 263,
726
+ "1": 264,
727
+ "2": 265,
728
+ "3": 266,
729
+ "4": 267,
730
+ "5": 268,
731
+ "6": 269,
732
+ "7": 270,
733
+ "8": 271,
734
+ "9": 272,
735
+ "<": 273,
736
+ "=": 274,
737
+ ">": 275,
738
+ "@": 276,
739
+ "A": 277,
740
+ "B": 278,
741
+ "C": 279,
742
+ "D": 280,
743
+ "E": 281,
744
+ "F": 282,
745
+ "G": 283,
746
+ "H": 284,
747
+ "I": 285,
748
+ "J": 286,
749
+ "K": 287,
750
+ "L": 288,
751
+ "M": 289,
752
+ "N": 290,
753
+ "O": 291,
754
+ "P": 292,
755
+ "Q": 293,
756
+ "R": 294,
757
+ "S": 295,
758
+ "T": 296,
759
+ "U": 297,
760
+ "V": 298,
761
+ "W": 299,
762
+ "X": 300,
763
+ "Y": 301,
764
+ "Z": 302,
765
+ "[": 303,
766
+ "\\": 304,
767
+ "]": 305,
768
+ "^": 306,
769
+ "_": 307,
770
+ "`": 308,
771
+ "{": 309,
772
+ "|": 310,
773
+ "}": 311,
774
+ "~": 312,
775
+ "‐": 313,
776
+ "‑": 314,
777
+ "‒": 315,
778
+ "–": 316,
779
+ "—": 317,
780
+ "―": 318,
781
+ "‖": 319,
782
+ "‗": 320,
783
+ "‘": 321,
784
+ "’": 322,
785
+ "‚": 323,
786
+ "‛": 324,
787
+ "“": 325,
788
+ "”": 326,
789
+ "„": 327,
790
+ "‟": 328,
791
+ " ": 329,
792
+ "¡": 330,
793
+ "¢": 331,
794
+ "£": 332,
795
+ "¤": 333,
796
+ "¥": 334,
797
+ "¦": 335,
798
+ "§": 336,
799
+ "¨": 337,
800
+ "©": 338,
801
+ "ª": 339,
802
+ "«": 340,
803
+ "¬": 341,
804
+ "­": 342,
805
+ "®": 343,
806
+ "¯": 344,
807
+ "°": 345,
808
+ "±": 346,
809
+ "²": 347,
810
+ "³": 348,
811
+ "´": 349,
812
+ "µ": 350,
813
+ "¶": 351,
814
+ "·": 352,
815
+ "¸": 353,
816
+ "¹": 354,
817
+ "º": 355,
818
+ "»": 356,
819
+ "¼": 357,
820
+ "½": 358,
821
+ "¾": 359,
822
+ "¿": 360,
823
+ "À": 361,
824
+ "Á": 362,
825
+ "Â": 363,
826
+ "Ã": 364,
827
+ "Ä": 365,
828
+ "Å": 366,
829
+ "Æ": 367,
830
+ "Ç": 368,
831
+ "È": 369,
832
+ "É": 370,
833
+ "Ê": 371,
834
+ "Ë": 372,
835
+ "Ì": 373,
836
+ "Í": 374,
837
+ "Î": 375,
838
+ "Ï": 376,
839
+ "Ð": 377,
840
+ "Ñ": 378,
841
+ "Ò": 379,
842
+ "Ó": 380,
843
+ "Ô": 381,
844
+ "Õ": 382,
845
+ "Ö": 383,
846
+ "×": 384,
847
+ "Ø": 385,
848
+ "Ù": 386,
849
+ "Ú": 387,
850
+ "Û": 388,
851
+ "Ü": 389,
852
+ "Ý": 390,
853
+ "Þ": 391,
854
+ "ß": 392,
855
+ "à": 393,
856
+ "á": 394,
857
+ "â": 395,
858
+ "ã": 396,
859
+ "ä": 397,
860
+ "å": 398,
861
+ "æ": 399,
862
+ "ç": 400,
863
+ "è": 401,
864
+ "é": 402,
865
+ "ê": 403,
866
+ "ë": 404,
867
+ "ì": 405,
868
+ "í": 406,
869
+ "î": 407,
870
+ "ï": 408,
871
+ "ð": 409,
872
+ "ñ": 410,
873
+ "ò": 411,
874
+ "ó": 412,
875
+ "ô": 413,
876
+ "õ": 414,
877
+ "ö": 415,
878
+ "÷": 416,
879
+ "ø": 417,
880
+ "ù": 418,
881
+ "ú": 419,
882
+ "û": 420,
883
+ "ü": 421,
884
+ "ý": 422,
885
+ "þ": 423,
886
+ "ÿ": 424,
887
+ "ɐ": 425,
888
+ "ɑ": 426,
889
+ "ɒ": 427,
890
+ "ɓ": 428,
891
+ "ɔ": 429,
892
+ "ɕ": 430,
893
+ "ɖ": 431,
894
+ "ɗ": 432,
895
+ "ɘ": 433,
896
+ "ə": 434,
897
+ "ɚ": 435,
898
+ "ɛ": 436,
899
+ "ɜ": 437,
900
+ "ɝ": 438,
901
+ "ɞ": 439,
902
+ "ɟ": 440,
903
+ "ɠ": 441,
904
+ "ɡ": 442,
905
+ "ɢ": 443,
906
+ "ɣ": 444,
907
+ "ɤ": 445,
908
+ "ɥ": 446,
909
+ "ɦ": 447,
910
+ "ɧ": 448,
911
+ "ɨ": 449,
912
+ "ɩ": 450,
913
+ "ɪ": 451,
914
+ "ɫ": 452,
915
+ "ɬ": 453,
916
+ "ɭ": 454,
917
+ "ɮ": 455,
918
+ "ɯ": 456,
919
+ "ɰ": 457,
920
+ "ɱ": 458,
921
+ "ɲ": 459,
922
+ "ɳ": 460,
923
+ "ɴ": 461,
924
+ "ɵ": 462,
925
+ "ɶ": 463,
926
+ "ɷ": 464,
927
+ "ɸ": 465,
928
+ "ɹ": 466,
929
+ "ɺ": 467,
930
+ "ɻ": 468,
931
+ "ɼ": 469,
932
+ "ɽ": 470,
933
+ "ɾ": 471,
934
+ "ɿ": 472,
935
+ "ʀ": 473,
936
+ "ʁ": 474,
937
+ "ʂ": 475,
938
+ "ʃ": 476,
939
+ "ʄ": 477,
940
+ "ʅ": 478,
941
+ "ʆ": 479,
942
+ "ʇ": 480,
943
+ "ʈ": 481,
944
+ "ʉ": 482,
945
+ "ʊ": 483,
946
+ "ʋ": 484,
947
+ "ʌ": 485,
948
+ "ʍ": 486,
949
+ "ʎ": 487,
950
+ "ʏ": 488,
951
+ "ʐ": 489,
952
+ "ʑ": 490,
953
+ "ʒ": 491,
954
+ "ʓ": 492,
955
+ "ʔ": 493,
956
+ "ʕ": 494,
957
+ "ʖ": 495,
958
+ "ʗ": 496,
959
+ "ʘ": 497,
960
+ "ʙ": 498,
961
+ "ʚ": 499,
962
+ "ʛ": 500,
963
+ "ʜ": 501,
964
+ "ʝ": 502,
965
+ "ʞ": 503,
966
+ "ʟ": 504,
967
+ "ʠ": 505,
968
+ "ʡ": 506,
969
+ "ʢ": 507,
970
+ "ʣ": 508,
971
+ "ʤ": 509,
972
+ "ʥ": 510,
973
+ "ʦ": 511,
974
+ "ʧ": 512,
975
+ "ʨ": 513,
976
+ "ʩ": 514,
977
+ "ʪ": 515,
978
+ "ʫ": 516,
979
+ "ʬ": 517,
980
+ "ʭ": 518,
981
+ "ʮ": 519,
982
+ "ʯ": 520,
983
+ "ʰ": 521,
984
+ "ʱ": 522,
985
+ "ʲ": 523,
986
+ "ʳ": 524,
987
+ "ʴ": 525,
988
+ "ʵ": 526,
989
+ "ʶ": 527,
990
+ "ʷ": 528,
991
+ "ʸ": 529,
992
+ "ʹ": 530,
993
+ "ʺ": 531,
994
+ "ʻ": 532,
995
+ "ʼ": 533,
996
+ "ʽ": 534,
997
+ "ʾ": 535,
998
+ "ʿ": 536,
999
+ "ˀ": 537,
1000
+ "ˁ": 538,
1001
+ "˂": 539,
1002
+ "˃": 540,
1003
+ "˄": 541,
1004
+ "˅": 542,
1005
+ "ˆ": 543,
1006
+ "ˇ": 544,
1007
+ "ˈ": 545,
1008
+ "ˉ": 546,
1009
+ "ˊ": 547,
1010
+ "ˋ": 548,
1011
+ "ˌ": 549,
1012
+ "ˍ": 550,
1013
+ "ˎ": 551,
1014
+ "ˏ": 552,
1015
+ "ː": 553,
1016
+ "ˑ": 554,
1017
+ "˒": 555,
1018
+ "˓": 556,
1019
+ "˔": 557,
1020
+ "˕": 558,
1021
+ "˖": 559,
1022
+ "˗": 560,
1023
+ "˘": 561,
1024
+ "˙": 562,
1025
+ "˚": 563,
1026
+ "˛": 564,
1027
+ "˜": 565,
1028
+ "˝": 566,
1029
+ "˞": 567,
1030
+ "˟": 568,
1031
+ "ˠ": 569,
1032
+ "ˡ": 570,
1033
+ "ˢ": 571,
1034
+ "ˣ": 572,
1035
+ "ˤ": 573,
1036
+ "˥": 574,
1037
+ "˦": 575,
1038
+ "˧": 576,
1039
+ "˨": 577,
1040
+ "˩": 578,
1041
+ "˪": 579,
1042
+ "˫": 580,
1043
+ "ˬ": 581,
1044
+ "˭": 582,
1045
+ "ˮ": 583,
1046
+ "˯": 584,
1047
+ "˰": 585,
1048
+ "˱": 586,
1049
+ "˲": 587,
1050
+ "˳": 588,
1051
+ "˴": 589,
1052
+ "˵": 590,
1053
+ "˶": 591,
1054
+ "˷": 592,
1055
+ "˸": 593,
1056
+ "˹": 594,
1057
+ "˺": 595,
1058
+ "˻": 596,
1059
+ "˼": 597,
1060
+ "˽": 598,
1061
+ "˾": 599,
1062
+ "˿": 600,
1063
+ "ā": 601,
1064
+ "ō": 602,
1065
+ "…": 603,
1066
+ "[UH]": 604,
1067
+ "[UM]": 605,
1068
+ "[giggle]": 606,
1069
+ "[laughter]": 607,
1070
+ "[guffaw]": 608,
1071
+ "[inhale]": 609,
1072
+ "[exhale]": 610,
1073
+ "[sigh]": 611,
1074
+ "[cry]": 612,
1075
+ "[bark]": 613,
1076
+ "[howl]": 614,
1077
+ "[meow]": 615,
1078
+ "[singing]": 616,
1079
+ "[music]": 617,
1080
+ "[whistle]": 618,
1081
+ "[humming]": 619,
1082
+ "[gasp]": 620,
1083
+ "[groan]": 621,
1084
+ "[whisper]": 622,
1085
+ "[mumble]": 623,
1086
+ "[sniff]": 624,
1087
+ "[sneeze]": 625,
1088
+ "[cough]": 626,
1089
+ "[snore]": 627,
1090
+ "[chew]": 628,
1091
+ "[sip]": 629,
1092
+ "[clear_throat]": 630,
1093
+ "[kiss]": 631,
1094
+ "[shhh]": 632,
1095
+ "[gibberish]": 633,
1096
+ "[fr]": 634,
1097
+ "[es]": 635,
1098
+ "[de]": 636,
1099
+ "[it]": 637,
1100
+ "[ipa]": 638,
1101
+ "[end_of_label]": 639,
1102
+ "ŋ": 640,
1103
+ "ᵻ": 641,
1104
+ "θ": 642,
1105
+ "̩": 643,
1106
+ "̃": 644,
1107
+ "ɑː": 645,
1108
+ "iː": 646,
1109
+ "uː": 647,
1110
+ "ɜː": 648,
1111
+ "ɔː": 649,
1112
+ "oː": 650,
1113
+ "eɪ": 651,
1114
+ "oʊ": 652,
1115
+ "aɪ": 653,
1116
+ "aʊ": 654,
1117
+ "ɔɪ": 655,
1118
+ "dʒ": 656,
1119
+ "tʃ": 657,
1120
+ "ɪŋ": 658,
1121
+ "ᵻd": 659,
1122
+ "ˈiː": 660,
1123
+ "ˌiː": 661,
1124
+ "ˈɪ": 662,
1125
+ "ˌɪ": 663,
1126
+ "ˈeɪ": 664,
1127
+ "ˌeɪ": 665,
1128
+ "ˈɛ": 666,
1129
+ "ˌɛ": 667,
1130
+ "ˈæ": 668,
1131
+ "ˌæ": 669,
1132
+ "ˈɑː": 670,
1133
+ "ˌɑː": 671,
1134
+ "ˈɔː": 672,
1135
+ "ˌɔː": 673,
1136
+ "oːɹ": 674,
1137
+ "ˈoːɹ": 675,
1138
+ "ˌoːɹ": 676,
1139
+ "ˈoʊ": 677,
1140
+ "ˌoʊ": 678,
1141
+ "ˈʊ": 679,
1142
+ "ˌʊ": 680,
1143
+ "ˈuː": 681,
1144
+ "ˌuː": 682,
1145
+ "ˈɜː": 683,
1146
+ "ˌɜː": 684,
1147
+ "ˈʌ": 685,
1148
+ "ˌʌ": 686,
1149
+ "ˈaɪ": 687,
1150
+ "ˌaɪ": 688,
1151
+ "ˈaʊ": 689,
1152
+ "ˌaʊ": 690,
1153
+ "ˈɔɪ": 691,
1154
+ "ˌɔɪ": 692,
1155
+ "ˈɚ": 693,
1156
+ "ˌɐ": 694,
1157
+ "[PLACEHOLDER55]": 695,
1158
+ "[PLACEHOLDER56]": 696,
1159
+ "[PLACEHOLDER57]": 697,
1160
+ "[PLACEHOLDER58]": 698,
1161
+ "[PLACEHOLDER59]": 699,
1162
+ "[PLACEHOLDER60]": 700,
1163
+ "[PLACEHOLDER61]": 701,
1164
+ "[PLACEHOLDER62]": 702,
1165
+ "[PLACEHOLDER63]": 703,
1166
+ "[s": 704,
1167
+ "[spac": 705,
1168
+ "[space]": 706,
1169
+ "[space]а": 707,
1170
+ "[space]ар": 708,
1171
+ "[space]б": 709,
1172
+ "[space]бо": 710,
1173
+ "[space]бу": 711,
1174
+ "[space]в": 712,
1175
+ "[space]в[space]": 713,
1176
+ "[space]в[space]с": 714,
1177
+ "[space]ва": 715,
1178
+ "[space]ви": 716,
1179
+ "[space]включ": 717,
1180
+ "[space]включи": 718,
1181
+ "[space]включи[space]": 719,
1182
+ "[space]во": 720,
1183
+ "[space]вос": 721,
1184
+ "[space]восемь": 722,
1185
+ "[space]вы": 723,
1186
+ "[space]г": 724,
1187
+ "[space]д": 725,
1188
+ "[space]два": 726,
1189
+ "[space]двадцать": 727,
1190
+ "[space]двадцать[space]": 728,
1191
+ "[space]две": 729,
1192
+ "[space]дев": 730,
1193
+ "[space]девять": 731,
1194
+ "[space]день": 732,
1195
+ "[space]дес": 733,
1196
+ "[space]ди": 734,
1197
+ "[space]до": 735,
1198
+ "[space]долла": 736,
1199
+ "[space]з": 737,
1200
+ "[space]за": 738,
1201
+ "[space]и": 739,
1202
+ "[space]и[space]": 740,
1203
+ "[space]к": 741,
1204
+ "[space]ка": 742,
1205
+ "[space]кар": 743,
1206
+ "[space]ки": 744,
1207
+ "[space]ко": 745,
1208
+ "[space]ку": 746,
1209
+ "[space]ли": 747,
1210
+ "[space]м": 748,
1211
+ "[space]ма": 749,
1212
+ "[space]манчестер": 750,
1213
+ "[space]мат": 751,
1214
+ "[space]ме": 752,
1215
+ "[space]ми": 753,
1216
+ "[space]мне": 754,
1217
+ "[space]мо": 755,
1218
+ "[space]можешь": 756,
1219
+ "[space]му": 757,
1220
+ "[space]на": 758,
1221
+ "[space]на[space]смотрешке": 759,
1222
+ "[space]на[space]тв": 760,
1223
+ "[space]най": 761,
1224
+ "[space]найдет": 762,
1225
+ "[space]но": 763,
1226
+ "[space]ноль": 764,
1227
+ "[space]о": 765,
1228
+ "[space]один": 766,
1229
+ "[space]от": 767,
1230
+ "[space]п": 768,
1231
+ "[space]па": 769,
1232
+ "[space]пер": 770,
1233
+ "[space]пере": 771,
1234
+ "[space]перев": 772,
1235
+ "[space]переда": 773,
1236
+ "[space]по": 774,
1237
+ "[space]под": 775,
1238
+ "[space]пос": 776,
1239
+ "[space]послед": 777,
1240
+ "[space]посмотре": 778,
1241
+ "[space]пре": 779,
1242
+ "[space]при": 780,
1243
+ "[space]про": 781,
1244
+ "[space]пят": 782,
1245
+ "[space]пять": 783,
1246
+ "[space]пятьдесят": 784,
1247
+ "[space]ре": 785,
1248
+ "[space]ро": 786,
1249
+ "[space]руб": 787,
1250
+ "[space]с": 788,
1251
+ "[space]са": 789,
1252
+ "[space]се": 790,
1253
+ "[space]сезо": 791,
1254
+ "[space]сезон": 792,
1255
+ "[space]сезона": 793,
1256
+ "[space]семь": 794,
1257
+ "[space]семьдесят": 795,
1258
+ "[space]сер": 796,
1259
+ "[space]сери": 797,
1260
+ "[space]сериал": 798,
1261
+ "[space]серия": 799,
1262
+ "[space]си": 800,
1263
+ "[space]ско": 801,
1264
+ "[space]сколько": 802,
1265
+ "[space]смотре": 803,
1266
+ "[space]смотреш": 804,
1267
+ "[space]смотрешке": 805,
1268
+ "[space]смотрешке[space]": 806,
1269
+ "[space]со": 807,
1270
+ "[space]сорок": 808,
1271
+ "[space]ст": 809,
1272
+ "[space]сто": 810,
1273
+ "[space]т": 811,
1274
+ "[space]та": 812,
1275
+ "[space]тв": 813,
1276
+ "[space]те": 814,
1277
+ "[space]теб": 815,
1278
+ "[space]теле": 816,
1279
+ "[space]телеви": 817,
1280
+ "[space]телевизо": 818,
1281
+ "[space]телевизоре": 819,
1282
+ "[space]телеканал": 820,
1283
+ "[space]телефо": 821,
1284
+ "[space]тре": 822,
1285
+ "[space]три": 823,
1286
+ "[space]три[space]": 824,
1287
+ "[space]тридцать": 825,
1288
+ "[space]ты": 826,
1289
+ "[space]тыся": 827,
1290
+ "[space]тысяч": 828,
1291
+ "[space]у": 829,
1292
+ "[space]ф": 830,
1293
+ "[space]фильм": 831,
1294
+ "[space]х": 832,
1295
+ "[space]ч": 833,
1296
+ "[space]четыре": 834,
1297
+ "[space]ш": 835,
1298
+ "[space]шесть": 836,
1299
+ "[space]э": 837,
1300
+ "[space]ю": 838,
1301
+ "[space]я": 839,
1302
+ "а": 840,
1303
+ "ай": 841,
1304
+ "ал": 842,
1305
+ "але": 843,
1306
+ "али": 844,
1307
+ "алиса": 845,
1308
+ "аль": 846,
1309
+ "ан": 847,
1310
+ "анд": 848,
1311
+ "ани": 849,
1312
+ "анчест": 850,
1313
+ "анчестер": 851,
1314
+ "ар": 852,
1315
+ "афи": 853,
1316
+ "афина": 854,
1317
+ "афина[space]": 855,
1318
+ "б": 856,
1319
+ "ба": 857,
1320
+ "бан": 858,
1321
+ "бе": 859,
1322
+ "бер": 860,
1323
+ "би": 861,
1324
+ "бо": 862,
1325
+ "бот": 863,
1326
+ "бу": 864,
1327
+ "будет": 865,
1328
+ "бы": 866,
1329
+ "в": 867,
1330
+ "ва": 868,
1331
+ "ве": 869,
1332
+ "вер": 870,
1333
+ "вет": 871,
1334
+ "ви": 872,
1335
+ "вич": 873,
1336
+ "включ": 874,
1337
+ "включи[space]": 875,
1338
+ "во": 876,
1339
+ "вой": 877,
1340
+ "ву": 878,
1341
+ "вы": 879,
1342
+ "вь": 880,
1343
+ "г": 881,
1344
+ "га": 882,
1345
+ "ге": 883,
1346
+ "ги": 884,
1347
+ "ги[space]": 885,
1348
+ "го": 886,
1349
+ "год": 887,
1350
+ "гра": 888,
1351
+ "гу": 889,
1352
+ "д": 890,
1353
+ "да": 891,
1354
+ "де": 892,
1355
+ "дев": 893,
1356
+ "дес": 894,
1357
+ "десят": 895,
1358
+ "дет": 896,
1359
+ "дж": 897,
1360
+ "джо": 898,
1361
+ "джой": 899,
1362
+ "джой[space]": 900,
1363
+ "ди": 901,
1364
+ "ди[space]": 902,
1365
+ "до": 903,
1366
+ "ду": 904,
1367
+ "дца": 905,
1368
+ "дцать": 906,
1369
+ "дцать[space]": 907,
1370
+ "ды": 908,
1371
+ "дь": 909,
1372
+ "е": 910,
1373
+ "е[space]": 911,
1374
+ "ев": 912,
1375
+ "еви": 913,
1376
+ "его": 914,
1377
+ "ез": 915,
1378
+ "ей": 916,
1379
+ "ел": 917,
1380
+ "ело": 918,
1381
+ "ем": 919,
1382
+ "емь": 920,
1383
+ "ен": 921,
1384
+ "ени": 922,
1385
+ "ент": 923,
1386
+ "ень": 924,
1387
+ "ер": 925,
1388
+ "ери": 926,
1389
+ "ес": 927,
1390
+ "ест": 928,
1391
+ "есть": 929,
1392
+ "есть[space]": 930,
1393
+ "есть[space]ли[space]": 931,
1394
+ "ет": 932,
1395
+ "еты": 933,
1396
+ "етыре": 934,
1397
+ "ешь": 935,
1398
+ "ж": 936,
1399
+ "жал": 937,
1400
+ "жалуйста": 938,
1401
+ "жан": 939,
1402
+ "жд": 940,
1403
+ "же": 941,
1404
+ "жешь": 942,
1405
+ "жи": 943,
1406
+ "жно": 944,
1407
+ "з": 945,
1408
+ "за": 946,
1409
+ "запу": 947,
1410
+ "зи": 948,
1411
+ "зна": 949,
1412
+ "зо": 950,
1413
+ "зод": 951,
1414
+ "зы": 952,
1415
+ "и": 953,
1416
+ "и[space]": 954,
1417
+ "и[space]м": 955,
1418
+ "и[space]мне": 956,
1419
+ "и[space]мне[space]": 957,
1420
+ "ив": 958,
1421
+ "из": 959,
1422
+ "ин": 960,
1423
+ "ит": 961,
1424
+ "ищ": 962,
1425
+ "й": 963,
1426
+ "й[space]": 964,
1427
+ "й[space]сезон": 965,
1428
+ "й[space]э": 966,
1429
+ "й[space]эпизод": 967,
1430
+ "к": 968,
1431
+ "ка": 969,
1432
+ "каж": 970,
1433
+ "кажи[space]": 971,
1434
+ "каза": 972,
1435
+ "казать": 973,
1436
+ "как": 974,
1437
+ "канал": 975,
1438
+ "кар": 976,
1439
+ "ке": 977,
1440
+ "ке[space]": 978,
1441
+ "ки": 979,
1442
+ "ки[space]": 980,
1443
+ "кие": 981,
1444
+ "кино": 982,
1445
+ "ключ": 983,
1446
+ "ко": 984,
1447
+ "ков": 985,
1448
+ "кой": 986,
1449
+ "ком": 987,
1450
+ "кро": 988,
1451
+ "кс": 989,
1452
+ "кто": 990,
1453
+ "ку": 991,
1454
+ "л": 992,
1455
+ "ла": 993,
1456
+ "лай": 994,
1457
+ "ле": 995,
1458
+ "лед": 996,
1459
+ "лей": 997,
1460
+ "лен": 998,
1461
+ "ли": 999,
1462
+ "ли[space]": 1000,
1463
+ "лий": 1001,
1464
+ "лла": 1002,
1465
+ "ло": 1003
1466
+ },
1467
+ "merges": [
1468
+ "t h",
1469
+ "i n",
1470
+ "th e",
1471
+ "a n",
1472
+ "e r",
1473
+ "o u",
1474
+ "r e",
1475
+ "o n",
1476
+ "a t",
1477
+ "e d",
1478
+ "e n",
1479
+ "t o",
1480
+ "in g",
1481
+ "an d",
1482
+ "i s",
1483
+ "a s",
1484
+ "a l",
1485
+ "o r",
1486
+ "o f",
1487
+ "a r",
1488
+ "i t",
1489
+ "e s",
1490
+ "h e",
1491
+ "s t",
1492
+ "l e",
1493
+ "o m",
1494
+ "s e",
1495
+ "b e",
1496
+ "a d",
1497
+ "o w",
1498
+ "l y",
1499
+ "c h",
1500
+ "w h",
1501
+ "th at",
1502
+ "y ou",
1503
+ "l i",
1504
+ "v e",
1505
+ "a c",
1506
+ "t i",
1507
+ "l d",
1508
+ "m e",
1509
+ "w as",
1510
+ "g h",
1511
+ "i d",
1512
+ "l l",
1513
+ "w i",
1514
+ "en t",
1515
+ "f or",
1516
+ "a y",
1517
+ "r o",
1518
+ "v er",
1519
+ "i c",
1520
+ "h er",
1521
+ "k e",
1522
+ "h is",
1523
+ "n o",
1524
+ "u t",
1525
+ "u n",
1526
+ "i r",
1527
+ "l o",
1528
+ "w e",
1529
+ "r i",
1530
+ "h a",
1531
+ "wi th",
1532
+ "gh t",
1533
+ "ou t",
1534
+ "i m",
1535
+ "i on",
1536
+ "al l",
1537
+ "a b",
1538
+ "on e",
1539
+ "n e",
1540
+ "g e",
1541
+ "ou ld",
1542
+ "t er",
1543
+ "m o",
1544
+ "h ad",
1545
+ "c e",
1546
+ "s he",
1547
+ "g o",
1548
+ "s h",
1549
+ "u r",
1550
+ "a m",
1551
+ "s o",
1552
+ "p e",
1553
+ "m y",
1554
+ "d e",
1555
+ "a re",
1556
+ "b ut",
1557
+ "om e",
1558
+ "f r",
1559
+ "the r",
1560
+ "f e",
1561
+ "s u",
1562
+ "d o",
1563
+ "c on",
1564
+ "t e",
1565
+ "a in",
1566
+ "er e",
1567
+ "p o",
1568
+ "i f",
1569
+ "the y",
1570
+ "u s",
1571
+ "a g",
1572
+ "t r",
1573
+ "n ow",
1574
+ "ou n",
1575
+ "th is",
1576
+ "ha ve",
1577
+ "no t",
1578
+ "s a",
1579
+ "i l",
1580
+ "u p",
1581
+ "th ing",
1582
+ "fr om",
1583
+ "a p",
1584
+ "h im",
1585
+ "ac k",
1586
+ "at ion",
1587
+ "an t",
1588
+ "ou r",
1589
+ "o p",
1590
+ "li ke",
1591
+ "u st",
1592
+ "es s",
1593
+ "b o",
1594
+ "o k",
1595
+ "u l",
1596
+ "in d",
1597
+ "e x",
1598
+ "c om",
1599
+ "s ome",
1600
+ "the re",
1601
+ "er s",
1602
+ "c o",
1603
+ "re s",
1604
+ "m an",
1605
+ "ar d",
1606
+ "p l",
1607
+ "w or",
1608
+ "w ay",
1609
+ "ti on",
1610
+ "f o",
1611
+ "c a",
1612
+ "w ere",
1613
+ "b y",
1614
+ "at e",
1615
+ "p ro",
1616
+ "t ed",
1617
+ "oun d",
1618
+ "ow n",
1619
+ "w ould",
1620
+ "t s",
1621
+ "wh at",
1622
+ "q u",
1623
+ "al ly",
1624
+ "i ght",
1625
+ "c k",
1626
+ "g r",
1627
+ "wh en",
1628
+ "v en",
1629
+ "c an",
1630
+ "ou gh",
1631
+ "in e",
1632
+ "en d",
1633
+ "p er",
1634
+ "ou s",
1635
+ "o d",
1636
+ "id e",
1637
+ "k now",
1638
+ "t y",
1639
+ "ver y",
1640
+ "s i",
1641
+ "a k",
1642
+ "wh o",
1643
+ "ab out",
1644
+ "i ll",
1645
+ "the m",
1646
+ "es t",
1647
+ "re d",
1648
+ "y e",
1649
+ "c ould",
1650
+ "on g",
1651
+ "you r",
1652
+ "the ir",
1653
+ "e m",
1654
+ "j ust",
1655
+ "o ther",
1656
+ "in to",
1657
+ "an y",
1658
+ "wh i",
1659
+ "u m",
1660
+ "t w",
1661
+ "as t",
1662
+ "d er",
1663
+ "d id",
1664
+ "i e",
1665
+ "be en",
1666
+ "ac e",
1667
+ "in k",
1668
+ "it y",
1669
+ "b ack",
1670
+ "t ing",
1671
+ "b r",
1672
+ "mo re",
1673
+ "a ke",
1674
+ "p p",
1675
+ "the n",
1676
+ "s p",
1677
+ "e l",
1678
+ "u se",
1679
+ "b l",
1680
+ "sa id",
1681
+ "o ver",
1682
+ "ge t",
1683
+ "ɑ ː",
1684
+ "i ː",
1685
+ "u ː",
1686
+ "ɜ ː",
1687
+ "ɔ ː",
1688
+ "o ː",
1689
+ "e ɪ",
1690
+ "o ʊ",
1691
+ "a ɪ",
1692
+ "a ʊ",
1693
+ "ɔ ɪ",
1694
+ "d ʒ",
1695
+ "t ʃ",
1696
+ "ɪ ŋ",
1697
+ "ᵻ d",
1698
+ "ˈ iː",
1699
+ "ˌ iː",
1700
+ "ˈ ɪ",
1701
+ "ˌ ɪ",
1702
+ "ˈ eɪ",
1703
+ "ˌ eɪ",
1704
+ "ˈ ɛ",
1705
+ "ˌ ɛ",
1706
+ "ˈ æ",
1707
+ "ˌ æ",
1708
+ "ˈ ɑː",
1709
+ "ˌ ɑː",
1710
+ "ˈ ɔː",
1711
+ "ˌ ɔː",
1712
+ "oː ɹ",
1713
+ "ˈ oːɹ",
1714
+ "ˌ oːɹ",
1715
+ "ˈ oʊ",
1716
+ "ˌ oʊ",
1717
+ "ˈ ʊ",
1718
+ "ˌ ʊ",
1719
+ "ˈ uː",
1720
+ "ˌ uː",
1721
+ "ˈ ɜː",
1722
+ "ˌ ɜː",
1723
+ "ˈ ʌ",
1724
+ "ˌ ʌ",
1725
+ "ˈ aɪ",
1726
+ "ˌ aɪ",
1727
+ "ˈ aʊ",
1728
+ "ˌ aʊ",
1729
+ "ˈ ɔɪ",
1730
+ "ˌ ɔɪ",
1731
+ "ˈ ɚ",
1732
+ "ˌ ɐ"
1733
+ ]
1734
+ }
1735
+ }
ru/chatterbox-ru-t3k/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
ru/chatterbox-ru-t3k/all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "eval_runtime": 5.7978,
4
+ "eval_samples_per_second": 0.862,
5
+ "eval_steps_per_second": 0.172,
6
+ "total_flos": 0.0,
7
+ "train_loss": 2.4700030918121336,
8
+ "train_runtime": 33124.2258,
9
+ "train_samples_per_second": 2.414,
10
+ "train_steps_per_second": 0.06
11
+ }
ru/chatterbox-ru-t3k/checkpoint-1200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fca9f6c9da56beb6a3b1f2798a579b13abb57477384cc8d8f1b9ae8affce884
3
+ size 2129654648
ru/chatterbox-ru-t3k/checkpoint-1200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3654e427631d4a610b52be1ecd3d8c28c0195f737c988a00cdfa12f73ff35573
3
+ size 4259421562
ru/chatterbox-ru-t3k/checkpoint-1200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da464937ba316d48ec9949d07484fd45b440ffa7234c330d726d67cebd362fc9
3
+ size 14244
ru/chatterbox-ru-t3k/checkpoint-1200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f2cfdd4644fc5166a75699380c870d3e26c0d4eb1d51bfb38fdf5956ed91f0
3
+ size 1064