Hugging Face's logo

vioannidis
/
wav2vec2-large-xls-r-300m-dutch-fast-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
3
vioannidis commited on
Commit
aba39df
·
1 Parent(s): 99db505

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -9
  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: 0.37981610317750925
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: 0.5065
36
- - Wer: 0.3798
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: 300
@@ -67,10 +67,11 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 4.463 | 0.68 | 200 | 2.9358 | 1.0 |
71
- | 1.8336 | 1.36 | 400 | 0.9449 | 0.6652 |
72
- | 0.332 | 2.03 | 600 | 0.6117 | 0.4496 |
73
- | 0.1614 | 2.71 | 800 | 0.5065 | 0.3798 |
 
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.3763171813336588
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: 0.4580
36
+ - Wer: 0.3763
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: 300
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 4.9018 | 0.58 | 200 | 2.9377 | 1.0 |
71
+ | 2.1148 | 1.15 | 400 | 1.1957 | 0.8662 |
72
+ | 0.7195 | 1.73 | 600 | 0.7060 | 0.5645 |
73
+ | 0.3888 | 2.31 | 800 | 0.5290 | 0.4377 |
74
+ | 0.2488 | 2.88 | 1000 | 0.4580 | 0.3763 |
75
 
76
 
77
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:747f5fdc4477aa57b30d7fa3de1f48c39222311e2b2990acb215ab90ef561c0a
3
  size 1262094573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef966c6f8233f7a6c90864cd1d83ee078f776a5b6db6f5f8a9a80a1dcf91e5b5
3
  size 1262094573