Hugging Face's logo

Jana0511
/
wav2vec2-large-xls-r-300m-welsh-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
1
Jana0511 commited on
Commit
8884dbb
·
1 Parent(s): 6ea307b

End of training

Browse files
Files changed (2) hide show
  1. README.md +28 -11
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -5,9 +5,24 @@ tags:
5
  - generated_from_trainer
6
  datasets:
7
  - common_voice
 
 
8
  model-index:
9
  - name: wav2vec2-large-xls-r-300m-welsh-colab
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,13 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  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.
19
  It achieves the following results on the evaluation set:
20
- - eval_loss: nan
21
- - eval_wer: 1.0
22
- - eval_runtime: 400.8204
23
- - eval_samples_per_second: 12.025
24
- - eval_steps_per_second: 1.504
25
- - epoch: 1.07
26
- - step: 400
27
 
28
  ## Model description
29
 
@@ -42,7 +52,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 0.03
46
  - train_batch_size: 8
47
  - eval_batch_size: 8
48
  - seed: 42
@@ -51,11 +61,18 @@ The following hyperparameters were used during training:
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_steps: 500
54
- - num_epochs: 10
 
 
 
 
 
 
 
55
 
56
  ### Framework versions
57
 
58
- - Transformers 4.32.0
59
  - Pytorch 2.0.1+cu118
60
  - Datasets 2.14.4
61
  - Tokenizers 0.13.3
 
5
  - generated_from_trainer
6
  datasets:
7
  - common_voice
8
+ metrics:
9
+ - wer
10
  model-index:
11
  - name: wav2vec2-large-xls-r-300m-welsh-colab
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice
18
+ type: common_voice
19
+ config: cy
20
+ split: test
21
+ args: cy
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.9999080142577901
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: 2.0522
36
+ - Wer: 0.9999
 
 
 
 
 
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
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
 
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: 3
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 4.6024 | 2.26 | 400 | 2.0522 | 0.9999 |
71
+
72
 
73
  ### Framework versions
74
 
75
+ - Transformers 4.32.1
76
  - Pytorch 2.0.1+cu118
77
  - Datasets 2.14.4
78
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cea43f2c87db6e81ed05d2afc9e3022a5f4776f6512d6b39dc3ef4d23e8f4d50
3
  size 1262090413
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fb051f5e401984a38d9aa6464514a6f15132932dba42e4b75ca18bd09ae41b3
3
  size 1262090413