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
b59ccb6
•
1 Parent(s): b7e7d4e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -14
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.5094757094757095
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: 1.1240
36
- - Wer: 0.5095
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: 0.0003
56
  - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
@@ -61,21 +61,15 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - num_epochs: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 5.1179 | 3.12 | 400 | 1.3528 | 0.8758 |
71
- | 0.8834 | 6.25 | 800 | 0.9791 | 0.6978 |
72
- | 0.4513 | 9.38 | 1200 | 0.9412 | 0.6085 |
73
- | 0.291 | 12.5 | 1600 | 1.0826 | 0.5874 |
74
- | 0.2133 | 15.62 | 2000 | 1.0616 | 0.5589 |
75
- | 0.1653 | 18.75 | 2400 | 1.0475 | 0.5519 |
76
- | 0.1235 | 21.88 | 2800 | 1.0702 | 0.5293 |
77
- | 0.0927 | 25.0 | 3200 | 1.1390 | 0.5219 |
78
- | 0.0698 | 28.12 | 3600 | 1.1240 | 0.5095 |
79
 
80
 
81
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.7804713804713804
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: 1.3812
36
+ - Wer: 0.7805
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.001
56
  - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 4.1427 | 3.12 | 400 | 1.6053 | 0.9481 |
71
+ | 1.1814 | 6.25 | 800 | 1.4622 | 0.8634 |
72
+ | 0.5771 | 9.38 | 1200 | 1.3812 | 0.7805 |
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions