Hugging Face's logo

Jour
/
train

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Model card Files
xet
Metrics Community
Jour commited on
Commit
6a67755
·
verified ·
1 Parent(s): a553ef9

Training in progress, step 20

Browse files
Files changed (8) hide show
  1. added_tokens.json +1 -7
  2. config.json +1 -1
  3. model.safetensors +2 -2
  4. runs/Jun08_15-49-57_jourdelune/events.out.tfevents.1717854597.jourdelune +2 -2
  5. runs/Jun08_15-59-12_jourdelune/events.out.tfevents.1717855152.jourdelune +3 -0
  6. special_tokens_map.json +107 -42
  7. tokenizer_config.json +107 -54
  8. training_args.bin +1 -1
added_tokens.json CHANGED
@@ -1605,11 +1605,5 @@
1605
  "<|vi|>": 50278,
1606
  "<|yi|>": 50335,
1607
  "<|yo|>": 50325,
1608
- "<|zh|>": 50260,
1609
- "[BRIDGE]": 51870,
1610
- "[CHORUS]": 51869,
1611
- "[VERSE 1]": 51865,
1612
- "[VERSE 2]": 51866,
1613
- "[VERSE 3]": 51867,
1614
- "[VERSE 4]": 51868
1615
  }
 
1605
  "<|vi|>": 50278,
1606
  "<|yi|>": 50335,
1607
  "<|yo|>": 50325,
1608
+ "<|zh|>": 50260
 
 
 
 
 
 
1609
  }
config.json CHANGED
@@ -150,5 +150,5 @@
150
  "transformers_version": "4.41.2",
151
  "use_cache": true,
152
  "use_weighted_layer_sum": false,
153
- "vocab_size": 51871
154
  }
 
150
  "transformers_version": "4.41.2",
151
  "use_cache": true,
152
  "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2956279aab54e9c46414565579bf8158055125fe8b754b73d2d8a4f442f25a2e
3
- size 151070888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba408df0a85a76f027e1cff9226f975a31cc885ed9da228bf2d2c0ff30f4286b
3
+ size 151061672
runs/Jun08_15-49-57_jourdelune/events.out.tfevents.1717854597.jourdelune CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d9b250cb6dbe541e0e39a97802a51c5e06f6a4b552e93f5eb44ca22a791fef1
3
- size 7649
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27afa584dee471264f1f832871627acc412079717e3ecadfe1d46a170f60ada7
3
+ size 8220
runs/Jun08_15-59-12_jourdelune/events.out.tfevents.1717855152.jourdelune ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b4dd1305caff91fa7a590794169bd4ef0eb928e8e9e1a86b6882566b1e2b1f
3
+ size 6507
special_tokens_map.json CHANGED
@@ -1,47 +1,112 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "[VERSE 1]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "[VERSE 2]",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "[VERSE 3]",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "[VERSE 4]",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- {
32
- "content": "[CHORUS]",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- },
38
- {
39
- "content": "[BRIDGE]",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ],
46
  "bos_token": {
47
  "content": "<|endoftext|>",
 
1
  {
2
  "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|he|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
  ],
111
  "bos_token": {
112
  "content": "<|endoftext|>",
tokenizer_config.json CHANGED
@@ -12865,63 +12865,116 @@
12865
  "rstrip": false,
12866
  "single_word": false,
12867
  "special": false
12868
- },
12869
- "51865": {
12870
- "content": "[VERSE 1]",
12871
- "lstrip": false,
12872
- "normalized": false,
12873
- "rstrip": false,
12874
- "single_word": false,
12875
- "special": true
12876
- },
12877
- "51866": {
12878
- "content": "[VERSE 2]",
12879
- "lstrip": false,
12880
- "normalized": false,
12881
- "rstrip": false,
12882
- "single_word": false,
12883
- "special": true
12884
- },
12885
- "51867": {
12886
- "content": "[VERSE 3]",
12887
- "lstrip": false,
12888
- "normalized": false,
12889
- "rstrip": false,
12890
- "single_word": false,
12891
- "special": true
12892
- },
12893
- "51868": {
12894
- "content": "[VERSE 4]",
12895
- "lstrip": false,
12896
- "normalized": false,
12897
- "rstrip": false,
12898
- "single_word": false,
12899
- "special": true
12900
- },
12901
- "51869": {
12902
- "content": "[CHORUS]",
12903
- "lstrip": false,
12904
- "normalized": false,
12905
- "rstrip": false,
12906
- "single_word": false,
12907
- "special": true
12908
- },
12909
- "51870": {
12910
- "content": "[BRIDGE]",
12911
- "lstrip": false,
12912
- "normalized": false,
12913
- "rstrip": false,
12914
- "single_word": false,
12915
- "special": true
12916
  }
12917
  },
12918
  "additional_special_tokens": [
12919
- "[VERSE 1]",
12920
- "[VERSE 2]",
12921
- "[VERSE 3]",
12922
- "[VERSE 4]",
12923
- "[CHORUS]",
12924
- "[BRIDGE]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12925
  ],
12926
  "bos_token": "<|endoftext|>",
12927
  "clean_up_tokenization_spaces": true,
 
12865
  "rstrip": false,
12866
  "single_word": false,
12867
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12868
  }
12869
  },
12870
  "additional_special_tokens": [
12871
+ "<|endoftext|>",
12872
+ "<|startoftranscript|>",
12873
+ "<|en|>",
12874
+ "<|zh|>",
12875
+ "<|de|>",
12876
+ "<|es|>",
12877
+ "<|ru|>",
12878
+ "<|ko|>",
12879
+ "<|fr|>",
12880
+ "<|ja|>",
12881
+ "<|pt|>",
12882
+ "<|tr|>",
12883
+ "<|pl|>",
12884
+ "<|ca|>",
12885
+ "<|nl|>",
12886
+ "<|ar|>",
12887
+ "<|sv|>",
12888
+ "<|it|>",
12889
+ "<|id|>",
12890
+ "<|hi|>",
12891
+ "<|fi|>",
12892
+ "<|vi|>",
12893
+ "<|he|>",
12894
+ "<|uk|>",
12895
+ "<|el|>",
12896
+ "<|ms|>",
12897
+ "<|cs|>",
12898
+ "<|ro|>",
12899
+ "<|da|>",
12900
+ "<|hu|>",
12901
+ "<|ta|>",
12902
+ "<|no|>",
12903
+ "<|th|>",
12904
+ "<|ur|>",
12905
+ "<|hr|>",
12906
+ "<|bg|>",
12907
+ "<|lt|>",
12908
+ "<|la|>",
12909
+ "<|mi|>",
12910
+ "<|ml|>",
12911
+ "<|cy|>",
12912
+ "<|sk|>",
12913
+ "<|te|>",
12914
+ "<|fa|>",
12915
+ "<|lv|>",
12916
+ "<|bn|>",
12917
+ "<|sr|>",
12918
+ "<|az|>",
12919
+ "<|sl|>",
12920
+ "<|kn|>",
12921
+ "<|et|>",
12922
+ "<|mk|>",
12923
+ "<|br|>",
12924
+ "<|eu|>",
12925
+ "<|is|>",
12926
+ "<|hy|>",
12927
+ "<|ne|>",
12928
+ "<|mn|>",
12929
+ "<|bs|>",
12930
+ "<|kk|>",
12931
+ "<|sq|>",
12932
+ "<|sw|>",
12933
+ "<|gl|>",
12934
+ "<|mr|>",
12935
+ "<|pa|>",
12936
+ "<|si|>",
12937
+ "<|km|>",
12938
+ "<|sn|>",
12939
+ "<|yo|>",
12940
+ "<|so|>",
12941
+ "<|af|>",
12942
+ "<|oc|>",
12943
+ "<|ka|>",
12944
+ "<|be|>",
12945
+ "<|tg|>",
12946
+ "<|sd|>",
12947
+ "<|gu|>",
12948
+ "<|am|>",
12949
+ "<|yi|>",
12950
+ "<|lo|>",
12951
+ "<|uz|>",
12952
+ "<|fo|>",
12953
+ "<|ht|>",
12954
+ "<|ps|>",
12955
+ "<|tk|>",
12956
+ "<|nn|>",
12957
+ "<|mt|>",
12958
+ "<|sa|>",
12959
+ "<|lb|>",
12960
+ "<|my|>",
12961
+ "<|bo|>",
12962
+ "<|tl|>",
12963
+ "<|mg|>",
12964
+ "<|as|>",
12965
+ "<|tt|>",
12966
+ "<|haw|>",
12967
+ "<|ln|>",
12968
+ "<|ha|>",
12969
+ "<|ba|>",
12970
+ "<|jw|>",
12971
+ "<|su|>",
12972
+ "<|translate|>",
12973
+ "<|transcribe|>",
12974
+ "<|startoflm|>",
12975
+ "<|startofprev|>",
12976
+ "<|nocaptions|>",
12977
+ "<|notimestamps|>"
12978
  ],
12979
  "bos_token": "<|endoftext|>",
12980
  "clean_up_tokenization_spaces": true,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d59d20fbe49c1bb914171e826b130e623a0c389c95aa3750098b4fe5136a697
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3785e011475409f6600e40215a1bed2b8047e367ee3032239ccdc5b8a7997cbb
3
  size 5240