Hugging Face's logo

yip-i
/
wav2vec2-demo-M01

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
1
yip-i commited on
Commit
51d04de
·
1 Parent(s): af060b4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: wav2vec2-demo-M01
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # wav2vec2-demo-M01
13
+
14
+ This model is a fine-tuned version of [yip-i/uaspeech-pretrained](https://huggingface.co/yip-i/uaspeech-pretrained) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 2.7099
17
+ - Wer: 1.4021
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0001
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_steps: 1000
43
+ - num_epochs: 30
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
48
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
49
+ | 7.3895 | 0.9 | 500 | 2.9817 | 1.0007 |
50
+ | 3.0164 | 1.8 | 1000 | 2.9513 | 1.2954 |
51
+ | 3.0307 | 2.7 | 1500 | 2.8709 | 1.3286 |
52
+ | 3.1314 | 3.6 | 2000 | 2.8754 | 1.0 |
53
+ | 3.0395 | 4.5 | 2500 | 2.9289 | 1.0 |
54
+ | 3.2647 | 5.41 | 3000 | 2.8134 | 1.0014 |
55
+ | 2.9821 | 6.31 | 3500 | 2.8370 | 1.3901 |
56
+ | 2.9262 | 7.21 | 4000 | 2.8731 | 1.3809 |
57
+ | 2.9982 | 8.11 | 4500 | 4.4794 | 1.3958 |
58
+ | 3.0807 | 9.01 | 5000 | 2.8268 | 1.3951 |
59
+ | 2.8873 | 9.91 | 5500 | 2.8014 | 1.5336 |
60
+ | 2.8755 | 10.81 | 6000 | 2.8010 | 1.3873 |
61
+ | 3.2618 | 11.71 | 6500 | 3.1033 | 1.3463 |
62
+ | 3.0063 | 12.61 | 7000 | 2.7906 | 1.3753 |
63
+ | 2.8481 | 13.51 | 7500 | 2.7874 | 1.3837 |
64
+ | 2.876 | 14.41 | 8000 | 2.8239 | 1.0636 |
65
+ | 2.8966 | 15.32 | 8500 | 2.7753 | 1.3915 |
66
+ | 2.8839 | 16.22 | 9000 | 2.7874 | 1.3223 |
67
+ | 2.8351 | 17.12 | 9500 | 2.7755 | 1.3915 |
68
+ | 2.8185 | 18.02 | 10000 | 2.7600 | 1.3908 |
69
+ | 2.8193 | 18.92 | 10500 | 2.7542 | 1.3915 |
70
+ | 2.8023 | 19.82 | 11000 | 2.7528 | 1.3915 |
71
+ | 2.7934 | 20.72 | 11500 | 2.7406 | 1.3915 |
72
+ | 2.8043 | 21.62 | 12000 | 2.7419 | 1.3915 |
73
+ | 2.7941 | 22.52 | 12500 | 2.7407 | 1.3915 |
74
+ | 2.7854 | 23.42 | 13000 | 2.7277 | 1.3915 |
75
+ | 2.7924 | 24.32 | 13500 | 2.7279 | 1.3915 |
76
+ | 2.7644 | 25.23 | 14000 | 2.7217 | 1.3915 |
77
+ | 2.7703 | 26.13 | 14500 | 2.7273 | 1.5032 |
78
+ | 2.7821 | 27.03 | 15000 | 2.7265 | 1.3915 |
79
+ | 2.7632 | 27.93 | 15500 | 2.7154 | 1.3915 |
80
+ | 2.749 | 28.83 | 16000 | 2.7125 | 1.3958 |
81
+ | 2.7515 | 29.73 | 16500 | 2.7099 | 1.4021 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.23.1
87
+ - Pytorch 1.12.1+cu113
88
+ - Datasets 1.18.3
89
+ - Tokenizers 0.13.2