Hugging Face's logo

yip-i
/
wav2vec2-demo-M04-2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
1
yip-i commited on
Commit
a6a7c47
·
1 Parent(s): 8f683aa

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: wav2vec2-demo-M04-2
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-M04-2
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: 2.0168
18
+ - Wer: 1.2882
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
+ | 21.8298 | 0.88 | 500 | 3.2643 | 1.0 |
51
+ | 3.2319 | 1.75 | 1000 | 2.8027 | 1.0 |
52
+ | 2.769 | 2.63 | 1500 | 2.4684 | 1.0 |
53
+ | 2.0823 | 3.5 | 2000 | 1.9137 | 1.6482 |
54
+ | 1.3094 | 4.38 | 2500 | 1.7267 | 1.6094 |
55
+ | 0.9654 | 5.25 | 3000 | 1.7523 | 1.4882 |
56
+ | 0.7505 | 6.13 | 3500 | 1.5588 | 1.5353 |
57
+ | 0.6364 | 7.01 | 4000 | 1.5428 | 1.4706 |
58
+ | 0.5307 | 7.88 | 4500 | 1.6277 | 1.4765 |
59
+ | 0.4664 | 8.76 | 5000 | 1.6817 | 1.3718 |
60
+ | 0.4243 | 9.63 | 5500 | 1.7682 | 1.4541 |
61
+ | 0.3911 | 10.51 | 6000 | 1.8567 | 1.4094 |
62
+ | 0.3555 | 11.38 | 6500 | 1.7248 | 1.3694 |
63
+ | 0.3252 | 12.26 | 7000 | 1.8712 | 1.4012 |
64
+ | 0.3072 | 13.13 | 7500 | 2.0088 | 1.4424 |
65
+ | 0.2956 | 14.01 | 8000 | 1.8649 | 1.3576 |
66
+ | 0.283 | 14.89 | 8500 | 1.8951 | 1.4035 |
67
+ | 0.2682 | 15.76 | 9000 | 1.8762 | 1.3976 |
68
+ | 0.2465 | 16.64 | 9500 | 1.8406 | 1.34 |
69
+ | 0.2344 | 17.51 | 10000 | 1.9975 | 1.3294 |
70
+ | 0.2269 | 18.39 | 10500 | 1.9207 | 1.3176 |
71
+ | 0.2053 | 19.26 | 11000 | 2.0406 | 1.3412 |
72
+ | 0.1934 | 20.14 | 11500 | 1.9039 | 1.2859 |
73
+ | 0.2018 | 21.02 | 12000 | 1.8337 | 1.3212 |
74
+ | 0.169 | 21.89 | 12500 | 1.9120 | 1.3071 |
75
+ | 0.1742 | 22.77 | 13000 | 2.0650 | 1.3153 |
76
+ | 0.1571 | 23.64 | 13500 | 2.0369 | 1.3165 |
77
+ | 0.1403 | 24.52 | 14000 | 2.0420 | 1.2894 |
78
+ | 0.1474 | 25.39 | 14500 | 1.9529 | 1.2847 |
79
+ | 0.1373 | 26.27 | 15000 | 2.0818 | 1.3129 |
80
+ | 0.1222 | 27.15 | 15500 | 1.9551 | 1.2753 |
81
+ | 0.1182 | 28.02 | 16000 | 2.0138 | 1.2659 |
82
+ | 0.1357 | 28.9 | 16500 | 1.9976 | 1.2859 |
83
+ | 0.1158 | 29.77 | 17000 | 2.0168 | 1.2882 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.23.1
89
+ - Pytorch 1.12.1+cu113
90
+ - Datasets 1.18.3
91
+ - Tokenizers 0.13.2