Hugging Face's logo

kreasof-ai
/
whisper-medium-bem2eng

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
cobrayyxx commited on
Commit
2b91ce2
·
verified ·
1 Parent(s): 46d8836

init model 10 epoch

Browse files
Files changed (3) hide show
  1. README.md +15 -11
  2. model.safetensors +1 -1
  3. runs/Apr05_02-29-41_0b155b856663/events.out.tfevents.1743820183.0b155b856663.12477.1 +2 -2
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](https://huggingface.co/openai/whisper-medium) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4530
22
- - Wer: 36.2003
23
 
24
  ## Model description
25
 
@@ -39,27 +39,31 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0001
42
- - train_batch_size: 48
43
- - eval_batch_size: 32
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_ratio: 0.03
48
- - num_epochs: 3
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
55
- | 0.4976 | 1.0 | 2069 | 0.4992 | 42.7909 |
56
- | 0.358 | 2.0 | 4138 | 0.4304 | 37.2852 |
57
- | 0.1891 | 3.0 | 6207 | 0.4530 | 36.2003 |
 
 
58
 
59
 
60
  ### Framework versions
61
 
62
  - Transformers 4.47.1
63
  - Pytorch 2.5.1+cu121
64
- - Datasets 3.5.0
65
  - Tokenizers 0.21.0
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6966
22
+ - Wer: 38.3922
23
 
24
  ## Model description
25
 
 
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
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 16
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.03
50
+ - num_epochs: 5
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|
57
+ | 1.172 | 1.0 | 6205 | 0.5755 | 47.5724 |
58
+ | 0.8696 | 2.0 | 12410 | 0.4932 | 40.5547 |
59
+ | 0.6827 | 3.0 | 18615 | 0.4860 | 38.7776 |
60
+ | 0.3563 | 4.0 | 24820 | 0.5455 | 38.3652 |
61
+ | 0.1066 | 5.0 | 31025 | 0.6966 | 38.3922 |
62
 
63
 
64
  ### Framework versions
65
 
66
  - Transformers 4.47.1
67
  - Pytorch 2.5.1+cu121
68
+ - Datasets 3.4.0
69
  - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3187c9649177f732c1e0c389584fb38e446628e555417508b0ee847cc1aa3fa
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d38f875f772e2638599f7d98a121d889e62bbfecc5347965e6a850b8136233b
3
  size 3055544304
runs/Apr05_02-29-41_0b155b856663/events.out.tfevents.1743820183.0b155b856663.12477.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed79a50030b6065824c1875c851d650745d5b4dbf6891791772f7fc168cd32f2
3
- size 140464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b058eec3c04e05497c2a7b987290373110426c1854658e82a66d6539ae40f6
3
+ size 140824