Hugging Face's logo

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

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
scarlett623 commited on
Commit
c314f10
•
1 Parent(s): abae06b

End of training

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-subset-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-subset-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-subset-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: 0.9394977168949772
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-subset-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: 1.3992
36
+ - Wer: 0.9395
37
+ - Cer: 0.3184
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 | 33.6533 | 1.0 | 1.0 |
72
+ | 70.5767 | 3.81 | 800 | 6.8140 | 1.0 | 1.0 |
73
+ | 7.1379 | 5.71 | 1200 | 6.5163 | 1.0 | 1.0 |
74
+ | 6.4771 | 7.62 | 1600 | 6.4602 | 1.0 | 1.0 |
75
+ | 6.3627 | 9.52 | 2000 | 6.3406 | 1.0 | 0.9700 |
76
+ | 6.3627 | 11.43 | 2400 | 6.1021 | 1.0 | 0.9678 |
77
+ | 6.1201 | 13.33 | 2800 | 5.1523 | 1.0 | 0.8385 |
78
+ | 5.3531 | 15.24 | 3200 | 4.2224 | 1.0 | 0.7084 |
79
+ | 4.1733 | 17.14 | 3600 | 3.6981 | 1.0 | 0.6332 |
80
+ | 3.5472 | 19.05 | 4000 | 3.2708 | 0.9994 | 0.5827 |
81
+ | 3.5472 | 20.95 | 4400 | 2.9629 | 0.9989 | 0.5510 |
82
+ | 3.0668 | 22.86 | 4800 | 2.7122 | 0.9943 | 0.5165 |
83
+ | 2.7248 | 24.76 | 5200 | 2.5171 | 0.9914 | 0.4976 |
84
+ | 2.4609 | 26.67 | 5600 | 2.3538 | 0.9897 | 0.4759 |
85
+ | 2.2323 | 28.57 | 6000 | 2.2112 | 0.9874 | 0.4555 |
86
+ | 2.2323 | 30.48 | 6400 | 2.0850 | 0.9834 | 0.4370 |
87
+ | 2.0438 | 32.38 | 6800 | 1.9982 | 0.9806 | 0.4261 |
88
+ | 1.8837 | 34.29 | 7200 | 1.9179 | 0.9766 | 0.4137 |
89
+ | 1.7646 | 36.19 | 7600 | 1.8278 | 0.9766 | 0.4030 |
90
+ | 1.6469 | 38.1 | 8000 | 1.7627 | 0.9755 | 0.3937 |
91
+ | 1.6469 | 40.0 | 8400 | 1.7063 | 0.9709 | 0.3853 |
92
+ | 1.5422 | 41.9 | 8800 | 1.6649 | 0.9663 | 0.3787 |
93
+ | 1.4561 | 43.81 | 9200 | 1.6336 | 0.9697 | 0.3714 |
94
+ | 1.3842 | 45.71 | 9600 | 1.5943 | 0.9606 | 0.3647 |
95
+ | 1.3164 | 47.62 | 10000 | 1.5681 | 0.9669 | 0.3621 |
96
+ | 1.3164 | 49.52 | 10400 | 1.5535 | 0.9600 | 0.3582 |
97
+ | 1.2654 | 51.43 | 10800 | 1.5354 | 0.9538 | 0.3544 |
98
+ | 1.2186 | 53.33 | 11200 | 1.5003 | 0.9555 | 0.3482 |
99
+ | 1.1781 | 55.24 | 11600 | 1.4979 | 0.9572 | 0.3473 |
100
+ | 1.1344 | 57.14 | 12000 | 1.4820 | 0.9549 | 0.3453 |
101
+ | 1.1344 | 59.05 | 12400 | 1.4707 | 0.9509 | 0.3396 |
102
+ | 1.0965 | 60.95 | 12800 | 1.4657 | 0.9509 | 0.3384 |
103
+ | 1.0637 | 62.86 | 13200 | 1.4610 | 0.9509 | 0.3371 |
104
+ | 1.0306 | 64.76 | 13600 | 1.4461 | 0.9509 | 0.3361 |
105
+ | 1.0014 | 66.67 | 14000 | 1.4437 | 0.9503 | 0.3328 |
106
+ | 1.0014 | 68.57 | 14400 | 1.4334 | 0.9463 | 0.3304 |
107
+ | 0.9758 | 70.48 | 14800 | 1.4267 | 0.9429 | 0.3295 |
108
+ | 0.9486 | 72.38 | 15200 | 1.4250 | 0.9469 | 0.3269 |
109
+ | 0.933 | 74.29 | 15600 | 1.4214 | 0.9441 | 0.3273 |
110
+ | 0.9121 | 76.19 | 16000 | 1.4161 | 0.9441 | 0.3267 |
111
+ | 0.9121 | 78.1 | 16400 | 1.4137 | 0.9446 | 0.3268 |
112
+ | 0.9001 | 80.0 | 16800 | 1.4216 | 0.9446 | 0.3253 |
113
+ | 0.8789 | 81.9 | 17200 | 1.4164 | 0.9435 | 0.3264 |
114
+ | 0.8659 | 83.81 | 17600 | 1.3996 | 0.9424 | 0.3216 |
115
+ | 0.8471 | 85.71 | 18000 | 1.4079 | 0.9458 | 0.3226 |
116
+ | 0.8471 | 87.62 | 18400 | 1.4042 | 0.9412 | 0.3214 |
117
+ | 0.8387 | 89.52 | 18800 | 1.4073 | 0.9424 | 0.3214 |
118
+ | 0.8299 | 91.43 | 19200 | 1.4005 | 0.9418 | 0.3192 |
119
+ | 0.8257 | 93.33 | 19600 | 1.4040 | 0.9406 | 0.3200 |
120
+ | 0.813 | 95.24 | 20000 | 1.4012 | 0.9412 | 0.3184 |
121
+ | 0.813 | 97.14 | 20400 | 1.4011 | 0.9389 | 0.3183 |
122
+ | 0.8062 | 99.05 | 20800 | 1.3992 | 0.9395 | 0.3184 |
123
+
124
+
125
  ### Framework versions
126
 
127
  - Transformers 4.32.0.dev0