Hugging Face's logo

7ocho
/
MondayBase

TensorBoard
Safetensors
whisper
Model card Files
xet
Metrics Community
7ocho commited on
Commit
4e2ef48
·
verified ·
1 Parent(s): 0f84bb9

Training in progress, step 1000

Browse files
Files changed (8) hide show
  1. config.json +57 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Dec07_14-30-59_d64ed016a372/events.out.tfevents.1765117863.d64ed016a372.21.0 +3 -0
  5. special_tokens_map.json +34 -0
  6. tokenizer_config.json +96 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "alignment_heads": [],
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "begin_suppress_tokens": null,
11
+ "bos_token_id": 1,
12
+ "classifier_proj_size": 256,
13
+ "d_model": 512,
14
+ "decoder_attention_heads": 8,
15
+ "decoder_ffn_dim": 2048,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 6,
18
+ "decoder_start_token_id": 1,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 8,
21
+ "encoder_ffn_dim": 2048,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 6,
24
+ "eos_token_id": 0,
25
+ "forced_decoder_ids": [
26
+ [
27
+ 1,
28
+ 3
29
+ ],
30
+ [
31
+ 2,
32
+ 5
33
+ ]
34
+ ],
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "mask_feature_length": 10,
38
+ "mask_feature_min_masks": 0,
39
+ "mask_feature_prob": 0.0,
40
+ "mask_time_length": 10,
41
+ "mask_time_min_masks": 2,
42
+ "mask_time_prob": 0.05,
43
+ "max_length": null,
44
+ "max_source_positions": 1500,
45
+ "max_target_positions": 448,
46
+ "median_filter_width": 7,
47
+ "model_type": "whisper",
48
+ "num_hidden_layers": 6,
49
+ "num_mel_bins": 80,
50
+ "pad_token_id": 0,
51
+ "scale_embedding": false,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.53.3",
54
+ "use_cache": true,
55
+ "use_weighted_layer_sum": false,
56
+ "vocab_size": 9975
57
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934ccb968cb0619a704a97fc801936230ef87710b4023f25297275f164e0524c
3
+ size 204612992
runs/Dec07_14-30-59_d64ed016a372/events.out.tfevents.1765117863.d64ed016a372.21.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f6b3396f65dfb00770e9a58d7d8875f346cf89f873e1cfd2527641a9c1cebb
3
+ size 14505
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|en|>",
4
+ "<|am|>",
5
+ "<|transcribe|>",
6
+ "<|translate|>",
7
+ "<|notimestamps|>",
8
+ "<|startofprev|>",
9
+ "<|nospeech|>",
10
+ "<|startoftranscript|>"
11
+ ],
12
+ "bos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": "<|endoftext|>",
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|startoftranscript|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|en|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<|am|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<|translate|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<|transcribe|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "7": {
53
+ "content": "<|startofprev|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "8": {
61
+ "content": "<|nospeech|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "9": {
69
+ "content": "<|notimestamps|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ }
76
+ },
77
+ "additional_special_tokens": [
78
+ "<|en|>",
79
+ "<|am|>",
80
+ "<|transcribe|>",
81
+ "<|translate|>",
82
+ "<|notimestamps|>",
83
+ "<|startofprev|>",
84
+ "<|nospeech|>",
85
+ "<|startoftranscript|>"
86
+ ],
87
+ "bos_token": "<|endoftext|>",
88
+ "clean_up_tokenization_spaces": false,
89
+ "eos_token": "<|endoftext|>",
90
+ "errors": "replace",
91
+ "extra_special_tokens": {},
92
+ "model_max_length": 1000000000000000019884624838656,
93
+ "pad_token": "<|endoftext|>",
94
+ "tokenizer_class": "WhisperTokenizer",
95
+ "unk_token": "<|endoftext|>"
96
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb60be886e13b95da4d17ec9dfbac2cd029dc69848c2a1fa617cb5965860779a
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff