Hugging Face's logo

scarlett623
/
wav2vec2-large-xlsr53-zh-cn-subset20-colab

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
scarlett623 commited on
Commit
959a513
•
1 Parent(s): 3274079

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -2
README.md CHANGED
@@ -3,9 +3,26 @@ license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
 
 
 
 
6
  model-index:
7
  - name: wav2vec2-large-xlsr53-zh-cn-subset20-colab
8
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # wav2vec2-large-xlsr53-zh-cn-subset20-colab
15
 
16
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -43,6 +64,64 @@ The following hyperparameters were used during training:
43
  - lr_scheduler_warmup_steps: 500
44
  - num_epochs: 100
45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  ### Framework versions
47
 
48
  - Transformers 4.32.0.dev0
 
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
6
+ datasets:
7
+ - common_voice
8
+ metrics:
9
+ - wer
10
  model-index:
11
  - name: wav2vec2-large-xlsr53-zh-cn-subset20-colab
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice
18
+ type: common_voice
19
+ config: zh-CN
20
+ split: test[:20%]
21
+ args: zh-CN
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.9503424657534246
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # wav2vec2-large-xlsr53-zh-cn-subset20-colab
32
 
33
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 2.0566
36
+ - Wer: 0.9503
37
+ - Cer: 0.3333
38
 
39
  ## Model description
40
 
 
64
  - lr_scheduler_warmup_steps: 500
65
  - num_epochs: 100
66
 
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
70
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
71
+ | No log | 1.9 | 400 | 6.7551 | 1.0 | 1.0 |
72
+ | 34.7845 | 3.81 | 800 | 6.4563 | 1.0 | 1.0 |
73
+ | 6.4358 | 5.71 | 1200 | 4.2319 | 1.0074 | 0.7454 |
74
+ | 4.2052 | 7.62 | 1600 | 2.6538 | 1.0200 | 0.5562 |
75
+ | 2.3906 | 9.52 | 2000 | 2.3565 | 1.0063 | 0.5147 |
76
+ | 2.3906 | 11.43 | 2400 | 2.1287 | 0.9863 | 0.4822 |
77
+ | 1.93 | 13.33 | 2800 | 1.9585 | 0.9812 | 0.4528 |
78
+ | 1.6322 | 15.24 | 3200 | 1.8771 | 0.9937 | 0.4381 |
79
+ | 1.3629 | 17.14 | 3600 | 1.8405 | 0.9926 | 0.4242 |
80
+ | 1.166 | 19.05 | 4000 | 1.7674 | 0.9989 | 0.4140 |
81
+ | 1.166 | 20.95 | 4400 | 1.7879 | 0.9795 | 0.4047 |
82
+ | 0.9915 | 22.86 | 4800 | 1.7597 | 1.0126 | 0.4080 |
83
+ | 0.8517 | 24.76 | 5200 | 1.7726 | 0.9829 | 0.3966 |
84
+ | 0.7143 | 26.67 | 5600 | 1.7623 | 0.9732 | 0.3863 |
85
+ | 0.6267 | 28.57 | 6000 | 1.8164 | 0.9720 | 0.3863 |
86
+ | 0.6267 | 30.48 | 6400 | 1.8136 | 0.9680 | 0.3801 |
87
+ | 0.5389 | 32.38 | 6800 | 1.8696 | 0.9652 | 0.3812 |
88
+ | 0.4764 | 34.29 | 7200 | 1.8625 | 0.9663 | 0.3744 |
89
+ | 0.4095 | 36.19 | 7600 | 1.8868 | 0.9618 | 0.3683 |
90
+ | 0.3594 | 38.1 | 8000 | 1.8834 | 0.9623 | 0.3699 |
91
+ | 0.3594 | 40.0 | 8400 | 1.9155 | 0.9589 | 0.3670 |
92
+ | 0.3064 | 41.9 | 8800 | 1.9268 | 0.9652 | 0.3688 |
93
+ | 0.2825 | 43.81 | 9200 | 1.9527 | 0.9697 | 0.3674 |
94
+ | 0.2524 | 45.71 | 9600 | 1.9726 | 0.9686 | 0.3617 |
95
+ | 0.2272 | 47.62 | 10000 | 1.9594 | 0.9629 | 0.3619 |
96
+ | 0.2272 | 49.52 | 10400 | 1.9799 | 0.9635 | 0.3607 |
97
+ | 0.2042 | 51.43 | 10800 | 2.0175 | 0.9669 | 0.3582 |
98
+ | 0.1975 | 53.33 | 11200 | 2.0246 | 0.9589 | 0.3571 |
99
+ | 0.1827 | 55.24 | 11600 | 2.0535 | 0.9703 | 0.3600 |
100
+ | 0.1677 | 57.14 | 12000 | 2.0458 | 0.9583 | 0.3555 |
101
+ | 0.1677 | 59.05 | 12400 | 2.0893 | 0.9572 | 0.3583 |
102
+ | 0.1626 | 60.95 | 12800 | 2.0729 | 0.9600 | 0.3557 |
103
+ | 0.155 | 62.86 | 13200 | 2.0706 | 0.9572 | 0.3538 |
104
+ | 0.1456 | 64.76 | 13600 | 2.0761 | 0.9532 | 0.3553 |
105
+ | 0.1337 | 66.67 | 14000 | 2.0349 | 0.9589 | 0.3474 |
106
+ | 0.1337 | 68.57 | 14400 | 2.0844 | 0.9549 | 0.3484 |
107
+ | 0.1274 | 70.48 | 14800 | 2.0874 | 0.9578 | 0.3505 |
108
+ | 0.1198 | 72.38 | 15200 | 2.0813 | 0.9526 | 0.3473 |
109
+ | 0.1164 | 74.29 | 15600 | 2.0866 | 0.9498 | 0.3473 |
110
+ | 0.1105 | 76.19 | 16000 | 2.0688 | 0.9486 | 0.3421 |
111
+ | 0.1105 | 78.1 | 16400 | 2.0854 | 0.9498 | 0.3431 |
112
+ | 0.1053 | 80.0 | 16800 | 2.0749 | 0.9503 | 0.3414 |
113
+ | 0.1 | 81.9 | 17200 | 2.0622 | 0.9543 | 0.3407 |
114
+ | 0.0977 | 83.81 | 17600 | 2.0678 | 0.9532 | 0.3396 |
115
+ | 0.0906 | 85.71 | 18000 | 2.0650 | 0.9515 | 0.3383 |
116
+ | 0.0906 | 87.62 | 18400 | 2.0631 | 0.9492 | 0.3378 |
117
+ | 0.0867 | 89.52 | 18800 | 2.0633 | 0.9521 | 0.3365 |
118
+ | 0.0836 | 91.43 | 19200 | 2.0606 | 0.9532 | 0.3346 |
119
+ | 0.0819 | 93.33 | 19600 | 2.0671 | 0.9538 | 0.3355 |
120
+ | 0.0768 | 95.24 | 20000 | 2.0661 | 0.9509 | 0.3338 |
121
+ | 0.0768 | 97.14 | 20400 | 2.0564 | 0.9498 | 0.3335 |
122
+ | 0.0752 | 99.05 | 20800 | 2.0566 | 0.9503 | 0.3333 |
123
+
124
+
125
  ### Framework versions
126
 
127
  - Transformers 4.32.0.dev0