Hugging Face's logo

kujirahand
/
whisper-medium-r22-e

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
English
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kujirahand commited on
Commit
5b2837c
·
1 Parent(s): eb958c3

Training in progress, step 50

Browse files
Files changed (6) hide show
  1. config.json +9 -9
  2. generation_config.json +22 -10
  3. pytorch_model-00001-of-00002.bin +3 -0
  4. pytorch_model-00002-of-00002.bin +3 -0
  5. pytorch_model.bin.index.json +0 -0
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-medium",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
@@ -13,17 +13,17 @@
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
- "d_model": 1024,
17
- "decoder_attention_heads": 16,
18
- "decoder_ffn_dim": 4096,
19
  "decoder_layerdrop": 0.0,
20
- "decoder_layers": 24,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
- "encoder_attention_heads": 16,
24
- "encoder_ffn_dim": 4096,
25
  "encoder_layerdrop": 0.0,
26
- "encoder_layers": 24,
27
  "eos_token_id": 50257,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
@@ -39,7 +39,7 @@
39
  "max_target_positions": 448,
40
  "median_filter_width": 7,
41
  "model_type": "whisper",
42
- "num_hidden_layers": 24,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
 
1
  {
2
+ "_name_or_path": "openai/whisper-large",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
13
  ],
14
  "bos_token_id": 50257,
15
  "classifier_proj_size": 256,
16
+ "d_model": 1280,
17
+ "decoder_attention_heads": 20,
18
+ "decoder_ffn_dim": 5120,
19
  "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 32,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
+ "encoder_attention_heads": 20,
24
+ "encoder_ffn_dim": 5120,
25
  "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 32,
27
  "eos_token_id": 50257,
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
 
39
  "max_target_positions": 448,
40
  "median_filter_width": 7,
41
  "model_type": "whisper",
42
+ "num_hidden_layers": 32,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
generation_config.json CHANGED
@@ -1,28 +1,40 @@
1
  {
2
  "alignment_heads": [
3
  [
4
- 13,
5
- 15
 
 
 
 
6
  ],
7
  [
8
- 15,
9
  4
10
  ],
11
  [
12
- 15,
13
- 15
 
 
 
 
14
  ],
15
  [
16
- 16,
17
- 1
18
  ],
19
  [
20
- 20,
21
- 0
22
  ],
23
  [
24
  23,
25
- 4
 
 
 
 
26
  ]
27
  ],
28
  "begin_suppress_tokens": [
 
1
  {
2
  "alignment_heads": [
3
  [
4
+ 9,
5
+ 19
6
+ ],
7
+ [
8
+ 11,
9
+ 2
10
  ],
11
  [
12
+ 11,
13
  4
14
  ],
15
  [
16
+ 11,
17
+ 17
18
+ ],
19
+ [
20
+ 22,
21
+ 7
22
  ],
23
  [
24
+ 22,
25
+ 11
26
  ],
27
  [
28
+ 22,
29
+ 17
30
  ],
31
  [
32
  23,
33
+ 2
34
+ ],
35
+ [
36
+ 23,
37
+ 15
38
  ]
39
  ],
40
  "begin_suppress_tokens": [
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195cc9a1f74856942ecb795c98d5d8ce94442b83b6a4f4d1568e05520468acc8
3
+ size 4992943617
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:159a6999a5ee6ffb36cd7020202c663d7dfcf1b76a8db3ee4fb7f49e92014d94
3
+ size 1180727888
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6352b9db6d94b3c51b5c2c20b5248447d31f935aae7b9684807aa1a2b5a20c8d
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a2990d4d130b42cf8fbfa7ba8f574eb43332601e76d83396fa2a0897d71d41
3
  size 4664