Hugging Face's logo

mediaProcessing
/
Transcriber-Medium

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
mediaProcessing commited on
Commit
fd4ae58
•
1 Parent(s): 3b43194

Training in progress, step 100

Browse files
Files changed (6) hide show
  1. config.json +9 -9
  2. pytorch_model.bin +2 -2
  3. runs/Aug16_15-57-58_mediaprocessin-MS-7D53/events.out.tfevents.1692215939.mediaprocessin-MS-7D53 +3 -0
  4. runs/Aug24_09-34-34_mediaprocessin-MS-7D53/events.out.tfevents.1692884077.mediaprocessin-MS-7D53 +3 -0
  5. runs/Aug24_10-12-17_mediaprocessin-MS-7D53/events.out.tfevents.1692886340.mediaprocessin-MS-7D53 +3 -0
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "openai/whisper-tiny",
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": 384,
17
- "decoder_attention_heads": 6,
18
- "decoder_ffn_dim": 1536,
19
  "decoder_layerdrop": 0.0,
20
- "decoder_layers": 4,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
- "encoder_attention_heads": 6,
24
- "encoder_ffn_dim": 1536,
25
  "encoder_layerdrop": 0.0,
26
- "encoder_layers": 4,
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": 4,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
 
1
  {
2
+ "_name_or_path": "openai/whisper-small",
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": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
  "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
  "decoder_start_token_id": 50258,
22
  "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
  "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
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": 12,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c67c681e4146b5688fa60c0f175400e4640b17964985d3ba543560602bf3f1bb
3
- size 151097459
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f568d07381bf947ead46ea97c22b5d2351eacffeae843b011b233fc133f5248
3
+ size 967099267
runs/Aug16_15-57-58_mediaprocessin-MS-7D53/events.out.tfevents.1692215939.mediaprocessin-MS-7D53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2ed0f62ab2f311b68cc52723e6a2208bb5b0196d8ba122c1f1c63c254e8c37
3
+ size 5077
runs/Aug24_09-34-34_mediaprocessin-MS-7D53/events.out.tfevents.1692884077.mediaprocessin-MS-7D53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46fba573afa0ea0df04db0c01e139a88a27803cab2679cf54ef2198df48ceb74
3
+ size 5075
runs/Aug24_10-12-17_mediaprocessin-MS-7D53/events.out.tfevents.1692886340.mediaprocessin-MS-7D53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041a495c6f9c66765117e9994ca6619b8ff15210654740c2e4d9a97416e7d89a
3
+ size 5691
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77d98d26135e8407e073c82e5057659e36c122de730fa10a299dbdd0fd8ab30c
3
  size 4271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed4d603182c91c71aac5ef523309b4be493017be9f06ddebe4d559a0e1599ea
3
  size 4271