Hugging Face's logo

sjhuskey
/
enenlhet-whisper-model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
sjhuskey commited on
Commit
2745345
·
verified ·
1 Parent(s): 00d6942

Model save

Browse files
Files changed (9) hide show
  1. README.md +9 -3
  2. added_tokens.json +0 -1
  3. config.json +2 -2
  4. generation_config.json +0 -1
  5. model.safetensors +2 -2
  6. runs/Jul14_21-10-34_04cc561c7ab8/events.out.tfevents.1752527463.04cc561c7ab8.4457.0 +3 -0
  7. special_tokens_map.json +7 -1
  8. tokenizer_config.json +1 -9
  9. training_args.bin +2 -2
README.md CHANGED
@@ -34,15 +34,21 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 1e-05
37
- - train_batch_size: 16
38
  - eval_batch_size: 8
39
  - seed: 42
 
 
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
- - lr_scheduler_warmup_steps: 200
43
- - training_steps: 3000
44
  - mixed_precision_training: Native AMP
45
 
 
 
 
 
46
  ### Framework versions
47
 
48
  - Transformers 4.48.0
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 1e-05
37
+ - train_batch_size: 4
38
  - eval_batch_size: 8
39
  - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 16
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 100
45
+ - num_epochs: 3
46
  - mixed_precision_training: Native AMP
47
 
48
+ ### Training results
49
+
50
+
51
+
52
  ### Framework versions
53
 
54
  - Transformers 4.48.0
added_tokens.json CHANGED
@@ -1568,7 +1568,6 @@
1568
  "<|notimestamps|>": 50363,
1569
  "<|no|>": 50288,
1570
  "<|oc|>": 50328,
1571
- "<|pad|>": 51865,
1572
  "<|pa|>": 50321,
1573
  "<|pl|>": 50269,
1574
  "<|ps|>": 50340,
 
1568
  "<|notimestamps|>": 50363,
1569
  "<|no|>": 50288,
1570
  "<|oc|>": 50328,
 
1571
  "<|pa|>": 50321,
1572
  "<|pl|>": 50269,
1573
  "<|ps|>": 50340,
config.json CHANGED
@@ -51,11 +51,11 @@
51
  "model_type": "whisper",
52
  "num_hidden_layers": 12,
53
  "num_mel_bins": 80,
54
- "pad_token_id": 51865,
55
  "scale_embedding": false,
56
  "torch_dtype": "float32",
57
  "transformers_version": "4.48.0",
58
  "use_cache": true,
59
  "use_weighted_layer_sum": false,
60
- "vocab_size": 51866
61
  }
 
51
  "model_type": "whisper",
52
  "num_hidden_layers": 12,
53
  "num_mel_bins": 80,
54
+ "pad_token_id": 50257,
55
  "scale_embedding": false,
56
  "torch_dtype": "float32",
57
  "transformers_version": "4.48.0",
58
  "use_cache": true,
59
  "use_weighted_layer_sum": false,
60
+ "vocab_size": 51865
61
  }
generation_config.json CHANGED
@@ -254,7 +254,6 @@
254
  50361,
255
  50362
256
  ],
257
- "task": "transcribe",
258
  "task_to_id": {
259
  "transcribe": 50359,
260
  "translate": 50358
 
254
  50361,
255
  50362
256
  ],
 
257
  "task_to_id": {
258
  "transcribe": 50359,
259
  "translate": 50358
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba1e551713187f7efec2dad768483ea9f6019a48fb363a7a051b6145ff1bc7ee
3
- size 966998152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde5bfd14e47cb11b8ce09d313774b4b241ff7957b2219482963e1297a21f7a0
3
+ size 966995080
runs/Jul14_21-10-34_04cc561c7ab8/events.out.tfevents.1752527463.04cc561c7ab8.4457.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f2ed7f54063117980a0d739f4f35aa2a4fde7918bd98c3bd0eca988c041091
3
+ size 7182
special_tokens_map.json CHANGED
@@ -122,7 +122,13 @@
122
  "rstrip": false,
123
  "single_word": false
124
  },
125
- "pad_token": "<|pad|>",
 
 
 
 
 
 
126
  "unk_token": {
127
  "content": "<|endoftext|>",
128
  "lstrip": false,
 
122
  "rstrip": false,
123
  "single_word": false
124
  },
125
+ "pad_token": {
126
+ "content": "<|endoftext|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
  "unk_token": {
133
  "content": "<|endoftext|>",
134
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -12865,14 +12865,6 @@
12865
  "rstrip": false,
12866
  "single_word": false,
12867
  "special": false
12868
- },
12869
- "51865": {
12870
- "content": "<|pad|>",
12871
- "lstrip": false,
12872
- "normalized": false,
12873
- "rstrip": false,
12874
- "single_word": false,
12875
- "special": true
12876
  }
12877
  },
12878
  "additional_special_tokens": [
@@ -12990,7 +12982,7 @@
12990
  "errors": "replace",
12991
  "extra_special_tokens": {},
12992
  "model_max_length": 1024,
12993
- "pad_token": "<|pad|>",
12994
  "processor_class": "WhisperProcessor",
12995
  "return_attention_mask": false,
12996
  "tokenizer_class": "WhisperTokenizer",
 
12865
  "rstrip": false,
12866
  "single_word": false,
12867
  "special": false
 
 
 
 
 
 
 
 
12868
  }
12869
  },
12870
  "additional_special_tokens": [
 
12982
  "errors": "replace",
12983
  "extra_special_tokens": {},
12984
  "model_max_length": 1024,
12985
+ "pad_token": "<|endoftext|>",
12986
  "processor_class": "WhisperProcessor",
12987
  "return_attention_mask": false,
12988
  "tokenizer_class": "WhisperTokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8148987a2cf6713a63cac2832a072d7cefae38eb77b4c20f4ac8017d7087afb7
3
- size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c82bef36d340d33d9b45056109e24f90c214102456d2ab85a6b2a386a319a7
3
+ size 5496