Hugging Face's logo

jcrkn
/
wav2vec2-large-xls-r-300m-breton-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jcrkn commited on
Commit
0fb65c9
•
1 Parent(s): 9c90090

End of training

Browse files
Files changed (2) hide show
  1. README.md +27 -16
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.5302549302549302
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.0737
36
- - Wer: 0.5303
37
 
38
  ## Model description
39
 
@@ -53,11 +53,11 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
- - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 32
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
@@ -67,17 +67,28 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 2.8658 | 2.68 | 400 | 1.2395 | 0.8972 |
71
- | 0.8219 | 5.37 | 800 | 0.9454 | 0.6731 |
72
- | 0.4743 | 8.05 | 1200 | 0.8880 | 0.6181 |
73
- | 0.3224 | 10.74 | 1600 | 0.9330 | 0.6148 |
74
- | 0.2415 | 13.42 | 2000 | 1.0494 | 0.5889 |
75
- | 0.1904 | 16.11 | 2400 | 1.0328 | 0.5469 |
76
- | 0.152 | 18.79 | 2800 | 1.0771 | 0.5625 |
77
- | 0.1231 | 21.48 | 3200 | 0.9980 | 0.5598 |
78
- | 0.0993 | 24.16 | 3600 | 1.0351 | 0.5317 |
79
- | 0.0788 | 26.85 | 4000 | 1.0560 | 0.5381 |
80
- | 0.0653 | 29.53 | 4400 | 1.0737 | 0.5303 |
 
 
 
 
 
 
 
 
 
 
 
81
 
82
 
83
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.4936988936988937
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.2211
36
+ - Wer: 0.4937
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
+ - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 16
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 5.3288 | 1.34 | 400 | 1.7076 | 0.9809 |
71
+ | 1.2014 | 2.69 | 800 | 1.0803 | 0.7733 |
72
+ | 0.7687 | 4.03 | 1200 | 0.9806 | 0.6642 |
73
+ | 0.5539 | 5.38 | 1600 | 0.9914 | 0.6301 |
74
+ | 0.4456 | 6.72 | 2000 | 0.9797 | 0.6265 |
75
+ | 0.3586 | 8.07 | 2400 | 1.0354 | 0.5803 |
76
+ | 0.2922 | 9.41 | 2800 | 0.9996 | 0.5821 |
77
+ | 0.2628 | 10.76 | 3200 | 1.0250 | 0.5708 |
78
+ | 0.2284 | 12.1 | 3600 | 1.0865 | 0.5722 |
79
+ | 0.1908 | 13.45 | 4000 | 1.0674 | 0.5450 |
80
+ | 0.1732 | 14.79 | 4400 | 1.1775 | 0.5614 |
81
+ | 0.153 | 16.13 | 4800 | 1.1542 | 0.5435 |
82
+ | 0.14 | 17.48 | 5200 | 1.1807 | 0.5449 |
83
+ | 0.1302 | 18.82 | 5600 | 1.1679 | 0.5376 |
84
+ | 0.1142 | 20.17 | 6000 | 1.1441 | 0.5276 |
85
+ | 0.104 | 21.51 | 6400 | 1.2243 | 0.5355 |
86
+ | 0.0882 | 22.86 | 6800 | 1.1837 | 0.5316 |
87
+ | 0.0807 | 24.2 | 7200 | 1.1986 | 0.5132 |
88
+ | 0.0744 | 25.55 | 7600 | 1.2182 | 0.5108 |
89
+ | 0.0646 | 26.89 | 8000 | 1.2116 | 0.5047 |
90
+ | 0.0551 | 28.24 | 8400 | 1.2009 | 0.4948 |
91
+ | 0.0503 | 29.58 | 8800 | 1.2211 | 0.4937 |
92
 
93
 
94
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:493d4f2712d1b65cccd37c32b1770ab6817a44281962f51410a4ab8f8897b63b
3
  size 1262078125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e66fc1d421bd0af7d33592591620f2385cc6ee05c3f8e6643f22b07baac6a4
3
  size 1262078125