Hugging Face's logo

yip-i
/
wav2vec2-demo-F03-2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
1
yip-i commited on
Commit
1f445db
·
1 Parent(s): eb935b4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-demo-F03-2
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-demo-F03-2
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.4472
18
+ - Wer: 0.8797
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
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
49
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
50
+ | 24.7815 | 0.97 | 500 | 3.3881 | 1.0 |
51
+ | 3.3791 | 1.94 | 1000 | 3.2550 | 1.0 |
52
+ | 2.9748 | 2.91 | 1500 | 2.8719 | 1.0 |
53
+ | 2.8305 | 3.88 | 2000 | 2.7878 | 1.0 |
54
+ | 2.6289 | 4.85 | 2500 | 2.5009 | 1.2082 |
55
+ | 2.1553 | 5.83 | 3000 | 1.8680 | 1.3270 |
56
+ | 1.4669 | 6.8 | 3500 | 1.5138 | 1.3266 |
57
+ | 1.0475 | 7.77 | 4000 | 1.3531 | 1.2078 |
58
+ | 0.8132 | 8.74 | 4500 | 1.2666 | 1.1926 |
59
+ | 0.665 | 9.71 | 5000 | 1.2461 | 1.0980 |
60
+ | 0.5538 | 10.68 | 5500 | 1.3152 | 1.0719 |
61
+ | 0.4759 | 11.65 | 6000 | 1.3190 | 1.0902 |
62
+ | 0.4221 | 12.62 | 6500 | 1.3077 | 1.0184 |
63
+ | 0.3836 | 13.59 | 7000 | 1.3410 | 1.0645 |
64
+ | 0.3409 | 14.56 | 7500 | 1.2378 | 1.0246 |
65
+ | 0.3068 | 15.53 | 8000 | 1.3002 | 1.0152 |
66
+ | 0.2911 | 16.5 | 8500 | 1.3603 | 1.0074 |
67
+ | 0.2647 | 17.48 | 9000 | 1.3479 | 0.9375 |
68
+ | 0.2446 | 18.45 | 9500 | 1.3462 | 0.9187 |
69
+ | 0.2208 | 19.42 | 10000 | 1.4029 | 0.9109 |
70
+ | 0.2203 | 20.39 | 10500 | 1.4036 | 0.8977 |
71
+ | 0.204 | 21.36 | 11000 | 1.3755 | 0.8668 |
72
+ | 0.191 | 22.33 | 11500 | 1.3042 | 0.8691 |
73
+ | 0.1784 | 23.3 | 12000 | 1.4343 | 0.8758 |
74
+ | 0.1692 | 24.27 | 12500 | 1.4351 | 0.8492 |
75
+ | 0.1527 | 25.24 | 13000 | 1.4415 | 0.8645 |
76
+ | 0.1444 | 26.21 | 13500 | 1.4684 | 0.8812 |
77
+ | 0.1432 | 27.18 | 14000 | 1.4406 | 0.8906 |
78
+ | 0.1385 | 28.16 | 14500 | 1.4900 | 0.8840 |
79
+ | 0.1392 | 29.13 | 15000 | 1.4472 | 0.8797 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.23.1
85
+ - Pytorch 1.12.1+cu113
86
+ - Datasets 1.18.3
87
+ - Tokenizers 0.13.2