Hugging Face's logo

menhior
/
wav2vec2-large-xls-r-300m-azeri-colab-main

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
menhior commited on
Commit
9176cb0
·
1 Parent(s): 319f2a0

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -12
  2. pytorch_model.bin +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 [menhior/wav2vec2-large-xls-r-300m-turkish-colab-full](https://huggingface.co/menhior/wav2vec2-large-xls-r-300m-turkish-colab-full) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.8177
21
- - Wer: 0.6451
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 9e-06
41
  - train_batch_size: 16
42
  - eval_batch_size: 8
43
  - seed: 42
@@ -52,15 +52,15 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 9.463 | 4.4 | 400 | 3.6305 | 1.0 |
56
- | 3.3799 | 8.79 | 800 | 3.2304 | 1.0 |
57
- | 3.1536 | 13.19 | 1200 | 2.9574 | 1.0 |
58
- | 2.2534 | 17.58 | 1600 | 1.4581 | 0.8751 |
59
- | 1.1535 | 21.98 | 2000 | 1.0185 | 0.7301 |
60
- | 0.8545 | 26.37 | 2400 | 0.9004 | 0.6787 |
61
- | 0.7337 | 30.77 | 2800 | 0.8527 | 0.6555 |
62
- | 0.6777 | 35.16 | 3200 | 0.8254 | 0.6513 |
63
- | 0.651 | 39.56 | 3600 | 0.8177 | 0.6451 |
64
 
65
 
66
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [menhior/wav2vec2-large-xls-r-300m-turkish-colab-full](https://huggingface.co/menhior/wav2vec2-large-xls-r-300m-turkish-colab-full) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5709
21
+ - Wer: 0.2893
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 8e-05
41
  - train_batch_size: 16
42
  - eval_batch_size: 8
43
  - seed: 42
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 5.6518 | 4.4 | 400 | 2.5189 | 1.0 |
56
+ | 0.638 | 8.79 | 800 | 0.4597 | 0.3461 |
57
+ | 0.1682 | 13.19 | 1200 | 0.4817 | 0.3135 |
58
+ | 0.0884 | 17.58 | 1600 | 0.4995 | 0.3111 |
59
+ | 0.0549 | 21.98 | 2000 | 0.5301 | 0.3018 |
60
+ | 0.0391 | 26.37 | 2400 | 0.5407 | 0.2949 |
61
+ | 0.0286 | 30.77 | 2800 | 0.5563 | 0.2959 |
62
+ | 0.0218 | 35.16 | 3200 | 0.5655 | 0.2893 |
63
+ | 0.0186 | 39.56 | 3600 | 0.5709 | 0.2893 |
64
 
65
 
66
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85ad5297fead564f26b0677c75478c2f1493088e46ee62b6489e9e15a9c99ff0
3
  size 1262102950
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206860b99b98db824a2577e2942c6dd3020b77c2ab1571a0c910e6d589083579
3
  size 1262102950