Hugging Face's logo

zoha
/
wav2vec2-base-timit-google-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
1
zoha commited on
Commit
659e1d0
·
1 Parent(s): d859c0a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-base-timit-google-colab
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # wav2vec2-base-timit-google-colab
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.4659
18
+ - Wer: 0.3080
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 30
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | 3.5787 | 0.87 | 500 | 1.7648 | 1.0305 |
52
+ | 0.8692 | 1.73 | 1000 | 0.5136 | 0.5103 |
53
+ | 0.4346 | 2.6 | 1500 | 0.4364 | 0.4515 |
54
+ | 0.31 | 3.46 | 2000 | 0.3889 | 0.4070 |
55
+ | 0.234 | 4.33 | 2500 | 0.4161 | 0.3863 |
56
+ | 0.2054 | 5.19 | 3000 | 0.3845 | 0.3722 |
57
+ | 0.165 | 6.06 | 3500 | 0.4035 | 0.3643 |
58
+ | 0.1436 | 6.92 | 4000 | 0.4090 | 0.3623 |
59
+ | 0.1381 | 7.79 | 4500 | 0.4007 | 0.3673 |
60
+ | 0.1175 | 8.65 | 5000 | 0.4588 | 0.3632 |
61
+ | 0.1052 | 9.52 | 5500 | 0.4441 | 0.3588 |
62
+ | 0.0988 | 10.38 | 6000 | 0.4133 | 0.3489 |
63
+ | 0.0877 | 11.25 | 6500 | 0.4758 | 0.3510 |
64
+ | 0.0856 | 12.11 | 7000 | 0.4454 | 0.3425 |
65
+ | 0.0731 | 12.98 | 7500 | 0.4252 | 0.3351 |
66
+ | 0.0712 | 13.84 | 8000 | 0.4163 | 0.3370 |
67
+ | 0.0711 | 14.71 | 8500 | 0.4166 | 0.3367 |
68
+ | 0.06 | 15.57 | 9000 | 0.4195 | 0.3347 |
69
+ | 0.0588 | 16.44 | 9500 | 0.4697 | 0.3367 |
70
+ | 0.0497 | 17.3 | 10000 | 0.4255 | 0.3314 |
71
+ | 0.0523 | 18.17 | 10500 | 0.4676 | 0.3307 |
72
+ | 0.0444 | 19.03 | 11000 | 0.4570 | 0.3244 |
73
+ | 0.0435 | 19.9 | 11500 | 0.4307 | 0.3243 |
74
+ | 0.0348 | 20.76 | 12000 | 0.4763 | 0.3245 |
75
+ | 0.036 | 21.63 | 12500 | 0.4635 | 0.3238 |
76
+ | 0.0347 | 22.49 | 13000 | 0.4602 | 0.3212 |
77
+ | 0.0333 | 23.36 | 13500 | 0.4472 | 0.3195 |
78
+ | 0.0311 | 24.22 | 14000 | 0.4449 | 0.3183 |
79
+ | 0.0294 | 25.09 | 14500 | 0.4631 | 0.3175 |
80
+ | 0.025 | 25.95 | 15000 | 0.4466 | 0.3164 |
81
+ | 0.023 | 26.82 | 15500 | 0.4581 | 0.3138 |
82
+ | 0.0216 | 27.68 | 16000 | 0.4665 | 0.3114 |
83
+ | 0.0198 | 28.55 | 16500 | 0.4590 | 0.3092 |
84
+ | 0.0181 | 29.41 | 17000 | 0.4659 | 0.3080 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.20.0.dev0
90
+ - Pytorch 1.11.0+cu113
91
+ - Datasets 1.18.3
92
+ - Tokenizers 0.12.1