语言:
- 乌尔都语
许可证: apache-2.0
标签:
- 自动语音识别
- mozilla-foundation/common_voice_8_0
- 训练生成
- 乌尔都语
- 鲁棒语音事件
- hf-asr排行榜
数据集:
- mozilla-foundation/common_voice_8_0
模型索引:
- 名称: ''
结果:
- 任务:
名称: 自动语音识别
类型: automatic-speech-recognition
数据集:
名称: Common Voice 8.0
类型: mozilla-foundation/common_voice_8_0
参数: 乌尔都语
指标:
- 名称: 测试WER
类型: wer
值: 47.38
该模型是基于HarrisDePerceptron/xls-r-300m-ur在MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - UR数据集上微调的版本。
在评估集上取得了以下结果:
- 损失: 1.0517
- 词错误率(WER): 0.5151291512915129
- 字符错误率(CER): 0.23689640940982254
模型描述
需要更多信息
预期用途与限制
需要更多信息
训练与评估数据
需要更多信息
训练过程
训练超参数
训练过程中使用了以下超参数:
- 学习率: 7.5e-05
- 训练批次大小: 8
- 评估批次大小: 8
- 随机种子: 42
- 梯度累积步数: 2
- 总训练批次大小: 16
- 优化器: Adam，参数β=(0.9,0.999)，ε=1e-08
- 学习率调度器类型: 线性
- 学习率预热步数: 100
- 训练轮数: 100.0
- 混合精度训练: 原生AMP
训练结果
| 训练损失 |
轮次 |
步数 |
验证损失 |
WER |
| 1.2991 |
1.96 |
100 |
0.9769 |
0.6627 |
| 1.3415 |
3.92 |
200 |
0.9701 |
0.6594 |
| 1.2998 |
5.88 |
300 |
0.9678 |
0.6668 |
| 1.2881 |
7.84 |
400 |
0.9650 |
0.6613 |
| 1.2369 |
9.8 |
500 |
0.9392 |
0.6502 |
| 1.2293 |
11.76 |
600 |
0.9536 |
0.6480 |
| 1.1709 |
13.73 |
700 |
0.9265 |
0.6402 |
| 1.1492 |
15.69 |
800 |
0.9636 |
0.6506 |
| 1.1044 |
17.65 |
900 |
0.9305 |
0.6351 |
| 1.0704 |
19.61 |
1000 |
0.9329 |
0.6280 |
| 1.0039 |
21.57 |
1100 |
0.9413 |
0.6295 |
| 0.9756 |
23.53 |
1200 |
0.9718 |
0.6185 |
| 0.9633 |
25.49 |
1300 |
0.9731 |
0.6133 |
| 0.932 |
27.45 |
1400 |
0.9659 |
0.6199 |
| 0.9252 |
29.41 |
1500 |
0.9766 |
0.6196 |
| 0.9172 |
31.37 |
1600 |
1.0052 |
0.6199 |
| 0.8733 |
33.33 |
1700 |
0.9955 |
0.6203 |
| 0.868 |
35.29 |
1800 |
1.0069 |
0.6240 |
| 0.8547 |
37.25 |
1900 |
0.9783 |
0.6258 |
| 0.8451 |
39.22 |
2000 |
0.9845 |
0.6052 |
| 0.8374 |
41.18 |
2100 |
0.9496 |
0.6137 |
| 0.8153 |
43.14 |
2200 |
0.9756 |
0.6122 |
| 0.8134 |
45.1 |
2300 |
0.9712 |
0.6096 |
| 0.8019 |
47.06 |
2400 |
0.9565 |
0.5970 |
| 0.7746 |
49.02 |
2500 |
0.9864 |
0.6096 |
| 0.7664 |
50.98 |
2600 |
0.9988 |
0.6092 |
| 0.7708 |
52.94 |
2700 |
1.0181 |
0.6255 |
| 0.7468 |
54.9 |
2800 |
0.9918 |
0.6148 |
| 0.7241 |
56.86 |
2900 |
1.0150 |
0.6018 |
| 0.7165 |
58.82 |
3000 |
1.0439 |
0.6063 |
| 0.7104 |
60.78 |
3100 |
1.0016 |
0.6037 |
| 0.6954 |
62.75 |
3200 |
1.0117 |
0.5970 |
| 0.6753 |
64.71 |
3300 |
1.0191 |
0.6037 |
| 0.6803 |
66.67 |
3400 |
1.0190 |
0.6033 |
| 0.661 |
68.63 |
3500 |
1.0284 |
0.6007 |
| 0.6597 |
70.59 |
3600 |
1.0060 |
0.5967 |
| 0.6398 |
72.55 |
3700 |
1.0372 |
0.6048 |
| 0.6105 |
74.51 |
3800 |
1.0048 |
0.6044 |
| 0.6164 |
76.47 |
3900 |
1.0398 |
0.6148 |
| 0.6354 |
78.43 |
4000 |
1.0272 |
0.6133 |
| 0.5952 |
80.39 |
4100 |
1.0364 |
0.6081 |
| 0.5814 |
82.35 |
4200 |
1.0418 |
0.6092 |
| 0.6079 |
84.31 |
4300 |
1.0277 |
0.5967 |
| 0.5748 |
86.27 |
4400 |
1.0362 |
0.6041 |
| 0.5624 |
88.24 |
4500 |
1.0427 |
0.6007 |
| 0.5767 |
90.2 |
4600 |
1.0370 |
0.5919 |
| 0.5793 |
92.16 |
4700 |
1.0442 |
0.6011 |
| 0.547 |
94.12 |
4800 |
1.0516 |
0.5982 |
| 0.5513 |
96.08 |
4900 |
1.0461 |
0.5989 |
| 0.5429 |
98.04 |
5000 |
1.0504 |
0.5996 |
| 0.5404 |
100.0 |
5100 |
1.0517 |
0.5967 |
框架版本
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.3
- Tokenizers 0.11.0
Transformers%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20none;%20}%20.st1%20{%20fill:%20%235ce6cf;%20}%20.st2%20{%20fill:%20%230080ff;%20}%20.st3%20{%20clip-path:%20url(%23clippath);%20}%20%3c/style%3e%3cclipPath%20id='clippath'%3e%3crect%20class='st0'%20y='0'%20width='120'%20height='32'/%3e%3c/clipPath%3e%3c/defs%3e%3cg%20class='st3'%3e%3cg%3e%3cpath%20class='st1'%20d='M22.4,32H3.2c-1,0-2-.5-2.6-1.4-.6-.9-.7-2-.4-2.9L9.8,2.1C10.3.8,11.5,0,12.8,0s2.5.8,3,2.1l9.6,25.6c.4,1,.2,2.1-.4,2.9-.6.9-1.6,1.4-2.6,1.4ZM7.8,25.6h10l-5-13.3-5,13.3Z'/%3e%3cpath%20class='st2'%20d='M33.6,32c-1.3,0-2.5-.8-3-2.1L21,4.3c-.6-1.7.2-3.5,1.9-4.1,1.7-.6,3.5.2,4.1,1.9l9.6,25.6c.6,1.7-.2,3.5-1.9,4.1-.4.1-.8.2-1.1.2h0Z'/%3e%3cpath%20d='M71.8,9.1h-6.9v4.6h6.9c2.5,0,4.6,2,4.6,4.6h-6.9c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h2.3c1.7,0,3.2-.4,4.6-1.2v1.2h4.6v-13.7c0-5-4.1-9.1-9.1-9.1h0ZM71.8,27.4h-2.3c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h6.9c0,2.5-2,4.6-4.6,4.6h0Z'/%3e%3cpath%20d='M52.3,9.1h-4.6V0h-4.6V32h9.1c5,0,9.1-4.1,9.1-9.1v-4.6c0-5.1-4.1-9.1-9.1-9.1h0ZM56.9,22.9c0,2.5-2,4.6-4.6,4.6h-4.6v-13.7h4.6c2.5,0,4.6,2,4.6,4.6v4.6h0Z'/%3e%3cpath%20d='M110.9,13.7h9.1v-4.6h-9.1c-5.1,0-9.1,4.1-9.1,9.1v4.6c0,5.1,4.1,9.1,9.1,9.1h9.1v-4.6h-9.1c-2.5,0-4.6-2-4.6-4.6h13.7v-4.6h-13.7c0-2.5,2-4.6,4.6-4.6h0Z'/%3e%3cpath%20d='M93.6,18.3h-4.6c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h10.3v-4.6h-10.3c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h4.6c1.3,0,2.3,1,2.3,2.3s-1,2.3-2.3,2.3h-10.3v4.6h10.3c3.8,0,6.9-3.1,6.9-6.9s-3.1-6.9-6.9-6.9Z'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)