Hugging Face's logo

jcrkn
/
wav2vec2-large-xls-r-300m-breton-colab_hyper2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
jcrkn commited on
Commit
09bf996
•
1 Parent(s): e5af315

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -10
  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: 0.7262145262145262
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: 0.9875
36
- - Wer: 0.7262
37
 
38
  ## Model description
39
 
@@ -67,13 +67,13 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 7.2936 | 0.67 | 200 | 3.1142 | 1.0 |
71
- | 3.042 | 1.34 | 400 | 2.9484 | 1.0 |
72
- | 2.3704 | 2.02 | 600 | 1.6178 | 0.9658 |
73
- | 1.4289 | 2.69 | 800 | 1.2506 | 0.8708 |
74
- | 1.1529 | 3.36 | 1000 | 1.1119 | 0.7989 |
75
- | 0.9827 | 4.03 | 1200 | 1.0284 | 0.7575 |
76
- | 0.8429 | 4.71 | 1400 | 0.9875 | 0.7262 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.6547378547378547
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: 0.9096
36
+ - Wer: 0.6547
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 6.8885 | 0.67 | 200 | 3.1346 | 1.0 |
71
+ | 3.0233 | 1.34 | 400 | 2.9296 | 1.0 |
72
+ | 2.0382 | 2.02 | 600 | 1.4167 | 0.9138 |
73
+ | 1.2087 | 2.69 | 800 | 1.1261 | 0.8175 |
74
+ | 0.9624 | 3.36 | 1000 | 1.0181 | 0.7453 |
75
+ | 0.7902 | 4.03 | 1200 | 0.9485 | 0.6942 |
76
+ | 0.6441 | 4.71 | 1400 | 0.9096 | 0.6547 |
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:b6c0f1f631ec374225fbf007670acf48f35e77eafdfb05661cf98941b07cd2e7
3
  size 1262078125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eb968b370baff5ba1a9e937ac32cfa6412938fb3c8a2d69d8cea1099c33a0a
3
  size 1262078125