Hugging Face's logo

monadical-labs
/
whisper-medium.en

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
ilokavat commited on
Commit
ef4cd2e
·
verified ·
1 Parent(s): 61e47ca

End of training

Browse files
Files changed (3) hide show
  1. README.md +18 -18
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.1237
22
- - Wer: 2.0990
23
 
24
  ## Model description
25
 
@@ -38,30 +38,30 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 5e-05
42
- - train_batch_size: 16
43
  - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - lr_scheduler_warmup_steps: 50
48
- - training_steps: 500
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 0.9094 | 50.0 | 50 | 1.2361 | 0.2822 |
56
- | 0.0029 | 100.0 | 100 | 1.1104 | 0.2822 |
57
- | 0.0001 | 150.0 | 150 | 1.3901 | 0.2525 |
58
- | 0.0001 | 200.0 | 200 | 1.8432 | 1.4059 |
59
- | 0.0001 | 250.0 | 250 | 2.2473 | 0.8713 |
60
- | 0.0 | 300.0 | 300 | 2.5626 | 2.0693 |
61
- | 0.0 | 350.0 | 350 | 2.8073 | 1.9307 |
62
- | 0.0 | 400.0 | 400 | 2.9786 | 2.0396 |
63
- | 0.0 | 450.0 | 450 | 3.0875 | 2.1634 |
64
- | 0.0 | 500.0 | 500 | 3.1237 | 2.0990 |
65
 
66
 
67
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5759
22
+ - Wer: 0.1630
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 25
48
+ - training_steps: 250
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 1.6889 | 0.5682 | 25 | 1.0935 | 0.2250 |
56
+ | 0.5293 | 1.1364 | 50 | 0.7940 | 0.4637 |
57
+ | 0.2548 | 1.7045 | 75 | 0.9126 | 0.2702 |
58
+ | 0.1804 | 2.2727 | 100 | 0.6907 | 0.1767 |
59
+ | 0.1173 | 2.8409 | 125 | 0.7136 | 0.1903 |
60
+ | 0.0631 | 3.4091 | 150 | 0.7046 | 0.1966 |
61
+ | 0.046 | 3.9773 | 175 | 0.6465 | 0.1872 |
62
+ | 0.029 | 4.5455 | 200 | 0.6110 | 0.3502 |
63
+ | 0.0107 | 5.1136 | 225 | 0.6141 | 0.1661 |
64
+ | 0.006 | 5.6818 | 250 | 0.5759 | 0.1630 |
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e429bf6cffc25860d7bcdea3158b38f7c445c1fef5e8c7faa4b39c4a30fdc26
3
  size 3055540208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ecab54b573e7e7dbfb930d4a69b734095fceb7ad350e7d8a725a80d3838462
3
  size 3055540208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1a2180c71b53bad29519b95aef24dcfb1b68ee5d1578d637a1ec0d2bd7d04ed
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5c4dbd65222300809f92f18541b68bfee75bce1d756729ee5ce4f0f84000f5
3
  size 5496