Hugging Face's logo

yyooggaa
/
whisper-tiny-id

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yyooggaa commited on
Commit
fafeed2
•
1 Parent(s): fdc166c

Model save

Browse files
Files changed (3) hide show
  1. README.md +12 -12
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4844
21
- - Wer: 90.6507
22
 
23
  ## Model description
24
 
@@ -38,8 +38,8 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
@@ -49,17 +49,17 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
54
- | 0.5003 | 1.93 | 1000 | 0.5082 | 64.1797 |
55
- | 0.2777 | 3.86 | 2000 | 0.4703 | 66.1938 |
56
- | 0.163 | 5.79 | 3000 | 0.4785 | 82.9806 |
57
- | 0.1078 | 7.72 | 4000 | 0.4844 | 90.6507 |
58
 
59
 
60
  ### Framework versions
61
 
62
- - Transformers 4.37.0.dev0
63
- - Pytorch 2.1.0+cu121
64
  - Datasets 2.16.1
65
  - Tokenizers 0.15.0
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5406
21
+ - Wer: 108.0794
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.3496 | 3.86 | 1000 | 0.4832 | 68.7427 |
55
+ | 0.1256 | 7.72 | 2000 | 0.4856 | 85.7807 |
56
+ | 0.0512 | 11.58 | 3000 | 0.5275 | 104.5165 |
57
+ | 0.0336 | 15.44 | 4000 | 0.5406 | 108.0794 |
58
 
59
 
60
  ### Framework versions
61
 
62
+ - Transformers 4.36.0
63
+ - Pytorch 2.0.0
64
  - Datasets 2.16.1
65
  - Tokenizers 0.15.0
generation_config.json CHANGED
@@ -243,5 +243,5 @@
243
  "transcribe": 50359,
244
  "translate": 50358
245
  },
246
- "transformers_version": "4.37.0.dev0"
247
  }
 
243
  "transcribe": 50359,
244
  "translate": 50358
245
  },
246
+ "transformers_version": "4.36.0"
247
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02fea30779d9224a966f175881badaf4409c058bf6129fdb24a81561c5eea941
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd461a7bbf84e4400e23eb7e8752a1e1523a5e5f1adc1387a8a95d07fb37b1a
3
  size 151061672