Hugging Face's logo

KatMarie
/
wav2vec2-large-xls-r-300m-eu

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
KatMarie commited on
Commit
490a2f5
•
1 Parent(s): 521b10a

End of training

Browse files
Files changed (2) hide show
  1. README.md +11 -11
  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: 0.7574981042282247
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 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5668
36
- - Wer: 0.7575
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 3e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
@@ -67,13 +67,13 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 5.6181 | 0.85 | 400 | 3.0028 | 1.0 |
71
- | 2.5912 | 1.7 | 800 | 1.6259 | 0.9999 |
72
- | 0.7428 | 2.56 | 1200 | 0.7843 | 0.8817 |
73
- | 0.4234 | 3.41 | 1600 | 0.5464 | 0.7827 |
74
- | 0.3273 | 4.26 | 2000 | 0.5232 | 0.7374 |
75
- | 0.2802 | 5.11 | 2400 | 0.6034 | 0.7839 |
76
- | 0.2499 | 5.96 | 2800 | 0.5668 | 0.7575 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.4967706508380619
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 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4355
36
+ - Wer: 0.4968
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.003
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 0.5405 | 0.85 | 400 | 0.8115 | 0.8949 |
71
+ | 0.5355 | 1.7 | 800 | 0.6292 | 0.7331 |
72
+ | 0.405 | 2.56 | 1200 | 0.5805 | 0.6699 |
73
+ | 0.3261 | 3.41 | 1600 | 0.5308 | 0.6513 |
74
+ | 0.2496 | 4.26 | 2000 | 0.4755 | 0.5850 |
75
+ | 0.1878 | 5.11 | 2400 | 0.4926 | 0.5448 |
76
+ | 0.1342 | 5.96 | 2800 | 0.4355 | 0.4968 |
77
 
78
 
79
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48105f3e5440bd938ec0cffd0dad7dbbc9174936e8bcbbaac551fb9858ac8ac6
3
  size 1262033069
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a48ab4fedc6a3c3c9800fc2f2649a7b1768e1dd73cdd74004b48d881b21815
3
  size 1262033069