Hugging Face's logo

uaremine
/
whisper-test-1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
uaremine commited on
Commit
6710fde
·
verified ·
1 Parent(s): acb223f

Training in progress, step 3000

Browse files
Files changed (6) hide show
  1. README.md +15 -14
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. runs/Mar28_08-58-44_MBC/events.out.tfevents.1711583925.MBC.18564.0 +2 -2
  6. training_args.bin +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.8434
19
- - Cer: 35.4552
20
 
21
  ## Model description
22
 
@@ -36,31 +36,32 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 1e-05
39
- - train_batch_size: 16
40
- - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 500
45
  - training_steps: 4000
 
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Cer |
50
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
- | 0.5441 | 2.79 | 500 | 0.6610 | 29.2804 |
52
- | 0.1453 | 5.59 | 1000 | 0.6771 | 28.8605 |
53
- | 0.0294 | 8.38 | 1500 | 0.7243 | 22.9719 |
54
- | 0.0087 | 11.17 | 2000 | 0.7784 | 28.9941 |
55
- | 0.0053 | 13.97 | 2500 | 0.8055 | 28.1065 |
56
- | 0.0035 | 16.76 | 3000 | 0.8247 | 35.0449 |
57
- | 0.0029 | 19.55 | 3500 | 0.8398 | 37.4022 |
58
- | 0.0026 | 22.35 | 4000 | 0.8434 | 35.4552 |
59
 
60
 
61
  ### Framework versions
62
 
63
- - Transformers 4.39.0
64
- - Pytorch 2.2.1
65
  - Datasets 2.18.0
66
  - Tokenizers 0.15.2
 
15
 
16
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.4267
19
+ - Cer: 30.5688
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 1e-05
39
+ - train_batch_size: 48
40
+ - eval_batch_size: 24
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 500
45
  - training_steps: 4000
46
+ - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Cer |
51
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
52
+ | 0.2285 | 8.33 | 500 | 0.6511 | 25.5392 |
53
+ | 0.0155 | 16.67 | 1000 | 0.7473 | 24.1172 |
54
+ | 0.0017 | 25.0 | 1500 | 0.8673 | 24.1840 |
55
+ | 0.0002 | 33.33 | 2000 | 1.0183 | 28.2497 |
56
+ | 0.0 | 41.67 | 2500 | 1.1707 | 28.3546 |
57
+ | 0.0 | 50.0 | 3000 | 1.3075 | 29.1850 |
58
+ | 0.0 | 58.33 | 3500 | 1.4029 | 29.7194 |
59
+ | 0.0 | 66.67 | 4000 | 1.4267 | 30.5688 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.39.1
65
+ - Pytorch 2.2.1+cu121
66
  - Datasets 2.18.0
67
  - Tokenizers 0.15.2
config.json CHANGED
@@ -45,7 +45,7 @@
45
  "scale_embedding": false,
46
  "suppress_tokens": [],
47
  "torch_dtype": "float32",
48
- "transformers_version": "4.39.0",
49
  "use_cache": true,
50
  "use_weighted_layer_sum": false,
51
  "vocab_size": 51865
 
45
  "scale_embedding": false,
46
  "suppress_tokens": [],
47
  "torch_dtype": "float32",
48
+ "transformers_version": "4.39.1",
49
  "use_cache": true,
50
  "use_weighted_layer_sum": false,
51
  "vocab_size": 51865
generation_config.json CHANGED
@@ -252,5 +252,5 @@
252
  "transcribe": 50359,
253
  "translate": 50358
254
  },
255
- "transformers_version": "4.39.0"
256
  }
 
252
  "transcribe": 50359,
253
  "translate": 50358
254
  },
255
+ "transformers_version": "4.39.1"
256
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af349754a58e6be7a581013f220f088929cc3d2eecf7799bda23c1f0cc31d72f
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed8fd27ca46dbc3eac69f035f5eb1b6684d7e1695b7d204e60f4749155376b8
3
  size 290403936
runs/Mar28_08-58-44_MBC/events.out.tfevents.1711583925.MBC.18564.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9f88b5f09d70d5f3f3950c918ed87e84e797211fe4a374c5a85c96be4b5abfe
3
- size 28080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4408d64848c85c4ea8a8bd093c88512c12fffb7e2248407997795500fb9fb67
3
+ size 32618
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b28115f3f890da2457f744dd86a7f0f0a6e2ce2fb6bd7083e645388f62d3de8
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7b6cb998a165299cb0a604207f238beeba14747f5e62eecdd4d3f2e666367e
3
  size 5112