Hugging Face's logo

gweltou
/
wav2vec2-xls-r-300m-br

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Breton
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
gweltou commited on
Commit
3c01bec
•
1 Parent(s): b2ea220

Model save

Browse files
Files changed (3) hide show
  1. README.md +44 -10
  2. model.safetensors +1 -1
  3. runs/Jun16_09-07-43_gweltaz-NUC10i7FNK/events.out.tfevents.1718521788.gweltaz-NUC10i7FNK.2874.0 +2 -2
README.md CHANGED
@@ -5,9 +5,24 @@ tags:
5
  - generated_from_trainer
6
  datasets:
7
  - common_voice_15_0
 
 
8
  model-index:
9
  - name: wav2vec2-xls-r-300m-br
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,14 +32,9 @@ 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_15_0 dataset.
19
  It achieves the following results on the evaluation set:
20
- - eval_loss: 0.7860
21
- - eval_wer: 53.4231
22
- - eval_cer: 18.5292
23
- - eval_runtime: 67.3553
24
- - eval_samples_per_second: 32.618
25
- - eval_steps_per_second: 4.083
26
- - epoch: 32.68
27
- - step: 15000
28
 
29
  ## Model description
30
 
@@ -43,7 +53,7 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 3e-05
47
  - train_batch_size: 8
48
  - eval_batch_size: 8
49
  - seed: 42
@@ -55,6 +65,30 @@ The following hyperparameters were used during training:
55
  - num_epochs: 40
56
  - mixed_precision_training: Native AMP
57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  ### Framework versions
59
 
60
  - Transformers 4.39.1
 
5
  - generated_from_trainer
6
  datasets:
7
  - common_voice_15_0
8
+ metrics:
9
+ - wer
10
  model-index:
11
  - name: wav2vec2-xls-r-300m-br
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice_15_0
18
+ type: common_voice_15_0
19
+ config: br
20
+ split: None
21
+ args: br
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 49.79811574697174
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_15_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.8887
36
+ - Wer: 49.7981
37
+ - Cer: 17.3877
 
 
 
 
 
38
 
39
  ## Model description
40
 
 
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
  - train_batch_size: 8
58
  - eval_batch_size: 8
59
  - seed: 42
 
65
  - num_epochs: 40
66
  - mixed_precision_training: Native AMP
67
 
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
71
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
72
+ | 5.1153 | 2.18 | 1000 | 2.8854 | 100.0 | 100.0 |
73
+ | 1.4117 | 4.36 | 2000 | 0.9161 | 71.2786 | 25.3180 |
74
+ | 0.7888 | 6.54 | 3000 | 0.7753 | 62.7456 | 22.0767 |
75
+ | 0.6316 | 8.71 | 4000 | 0.7550 | 58.1786 | 20.5383 |
76
+ | 0.5434 | 10.89 | 5000 | 0.7508 | 56.5096 | 20.1168 |
77
+ | 0.4672 | 13.07 | 6000 | 0.7844 | 54.9125 | 19.3835 |
78
+ | 0.4237 | 15.25 | 7000 | 0.7786 | 53.2705 | 18.5765 |
79
+ | 0.3899 | 17.43 | 8000 | 0.8050 | 53.0552 | 18.6105 |
80
+ | 0.3607 | 19.61 | 9000 | 0.8280 | 51.9874 | 18.3024 |
81
+ | 0.3355 | 21.79 | 10000 | 0.7967 | 51.5388 | 17.9811 |
82
+ | 0.3098 | 23.97 | 11000 | 0.8296 | 51.2876 | 17.9547 |
83
+ | 0.2937 | 26.14 | 12000 | 0.8544 | 50.9915 | 17.7827 |
84
+ | 0.2793 | 28.32 | 13000 | 0.8909 | 51.5478 | 18.1286 |
85
+ | 0.2641 | 30.5 | 14000 | 0.8740 | 50.4800 | 17.6561 |
86
+ | 0.2552 | 32.68 | 15000 | 0.8832 | 49.9776 | 17.4463 |
87
+ | 0.2467 | 34.86 | 16000 | 0.8753 | 50.3096 | 17.4765 |
88
+ | 0.2378 | 37.04 | 17000 | 0.8895 | 49.8789 | 17.3952 |
89
+ | 0.2337 | 39.22 | 18000 | 0.8887 | 49.7981 | 17.3877 |
90
+
91
+
92
  ### Framework versions
93
 
94
  - Transformers 4.39.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1690a7b513b78fe10eceb331cbf313db42d51da28be18ee7c720a88c36c2c825
3
  size 1262012432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618d70324160c092d234954f9c58afcc76a89575cc15143857f7b8e76d0ddb13
3
  size 1262012432
runs/Jun16_09-07-43_gweltaz-NUC10i7FNK/events.out.tfevents.1718521788.gweltaz-NUC10i7FNK.2874.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c3f181118d46a62dc49c8439d2ccd9a40ac494f93355775863b8629b541f36b
3
- size 15904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd5c620f3c5fad0b6bb08ca7e47da6c61f64617c48de5d7375324de97cd546b
3
+ size 16851