Hugging Face's logo

adrianSauer
/
wav2vec2-wer

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Guaraní
wav2vec2
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
adrianSauer commited on
Commit
1965285
·
verified ·
1 Parent(s): 6aa01a5

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -13
README.md CHANGED
@@ -19,12 +19,12 @@ model-index:
19
  name: Common Voice 16
20
  type: mozilla-foundation/common_voice_16_1
21
  config: gn
22
- split: test
23
  args: gn
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 43.723554301833566
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [glob-asr/wav2vec2-large-xls-r-300m-guarani-small](https://huggingface.co/glob-asr/wav2vec2-large-xls-r-300m-guarani-small) on the Common Voice 16 dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.3202
38
- - Wer: 43.7236
39
 
40
  ## Model description
41
 
@@ -55,9 +55,11 @@ More information needed
55
 
56
  The following hyperparameters were used during training:
57
  - learning_rate: 1e-05
58
- - train_batch_size: 16
59
  - eval_batch_size: 16
60
  - seed: 42
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: constant_with_warmup
63
  - lr_scheduler_warmup_steps: 50
@@ -68,16 +70,16 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:------:|:----:|:---------------:|:-------:|
71
- | 0.4174 | 1.0101 | 100 | 0.3535 | 47.6728 |
72
- | 0.3411 | 2.0202 | 200 | 0.3387 | 46.3188 |
73
- | 0.2905 | 3.0303 | 300 | 0.3278 | 45.7546 |
74
- | 0.2591 | 4.0404 | 400 | 0.3214 | 44.6544 |
75
- | 0.251 | 5.0505 | 500 | 0.3202 | 43.7236 |
76
 
77
 
78
  ### Framework versions
79
 
80
- - Transformers 4.40.1
81
- - Pytorch 2.2.1+cu121
82
- - Datasets 2.19.0
83
  - Tokenizers 0.19.1
 
19
  name: Common Voice 16
20
  type: mozilla-foundation/common_voice_16_1
21
  config: gn
22
+ split: None
23
  args: gn
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 49.766822118587605
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
 
35
  This model is a fine-tuned version of [glob-asr/wav2vec2-large-xls-r-300m-guarani-small](https://huggingface.co/glob-asr/wav2vec2-large-xls-r-300m-guarani-small) on the Common Voice 16 dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.3513
38
+ - Wer: 49.7668
39
 
40
  ## Model description
41
 
 
55
 
56
  The following hyperparameters were used during training:
57
  - learning_rate: 1e-05
58
+ - train_batch_size: 8
59
  - eval_batch_size: 16
60
  - seed: 42
61
+ - gradient_accumulation_steps: 2
62
+ - total_train_batch_size: 16
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: constant_with_warmup
65
  - lr_scheduler_warmup_steps: 50
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer |
72
  |:-------------:|:------:|:----:|:---------------:|:-------:|
73
+ | 0.4171 | 1.0152 | 100 | 0.3798 | 55.2965 |
74
+ | 0.3376 | 2.0305 | 200 | 0.3628 | 53.8974 |
75
+ | 0.294 | 3.0457 | 300 | 0.3528 | 52.4983 |
76
+ | 0.2632 | 4.0609 | 400 | 0.3484 | 49.7668 |
77
+ | 0.2459 | 5.0761 | 500 | 0.3513 | 49.7668 |
78
 
79
 
80
  ### Framework versions
81
 
82
+ - Transformers 4.44.0
83
+ - Pytorch 2.3.1+cu121
84
+ - Datasets 2.21.0
85
  - Tokenizers 0.19.1