语言:
- 乌尔都语
许可证: apache-2.0
标签:
- 自动语音识别
- mozilla-foundation/common_voice_7_0
- 训练生成
数据集:
- common_voice
模型索引:
- 名称: ''
结果: []
该模型是在MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UR数据集上对facebook/wav2vec2-xls-r-300m进行微调的版本。在评估集上取得了以下结果：
- 损失值: 1.2924
- 词错误率(WER): 0.7201
模型描述
需补充更多信息
预期用途与限制
需补充更多信息
训练与评估数据
需补充更多信息
训练流程
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 (beta1=0.9, beta2=0.999, epsilon=1e-08)
- 学习率调度器类型: 线性
- 学习率预热步数: 100
- 训练轮数: 200.0
- 混合精度训练: Native AMP
训练结果
| 训练损失 |
训练轮数 |
步数 |
验证损失 |
词错误率 |
| 11.2783 |
4.17 |
100 |
4.6409 |
1.0 |
| 3.5578 |
8.33 |
200 |
3.1649 |
1.0 |
| 3.1279 |
12.5 |
300 |
3.0335 |
1.0 |
| 2.9944 |
16.67 |
400 |
2.9526 |
0.9983 |
| 2.9275 |
20.83 |
500 |
2.9291 |
1.0009 |
| 2.8077 |
25.0 |
600 |
2.5633 |
0.9895 |
| 2.4438 |
29.17 |
700 |
1.9045 |
0.9564 |
| 1.9659 |
33.33 |
800 |
1.4114 |
0.7960 |
| 1.7092 |
37.5 |
900 |
1.2584 |
0.7637 |
| 1.517 |
41.67 |
1000 |
1.2040 |
0.7507 |
| 1.3966 |
45.83 |
1100 |
1.1273 |
0.7463 |
| 1.3197 |
50.0 |
1200 |
1.1054 |
0.6957 |
| 1.2476 |
54.17 |
1300 |
1.1035 |
0.7001 |
| 1.1796 |
58.33 |
1400 |
1.0890 |
0.7097 |
| 1.1237 |
62.5 |
1500 |
1.0883 |
0.7167 |
| 1.0777 |
66.67 |
1600 |
1.1067 |
0.7219 |
| 1.0051 |
70.83 |
1700 |
1.1115 |
0.7236 |
| 0.9521 |
75.0 |
1800 |
1.0867 |
0.7132 |
| 0.9147 |
79.17 |
1900 |
1.0852 |
0.7210 |
| 0.8798 |
83.33 |
2000 |
1.1411 |
0.7097 |
| 0.8317 |
87.5 |
2100 |
1.1634 |
0.7018 |
| 0.7946 |
91.67 |
2200 |
1.1621 |
0.7201 |
| 0.7594 |
95.83 |
2300 |
1.1482 |
0.7036 |
| 0.729 |
100.0 |
2400 |
1.1493 |
0.7062 |
| 0.7055 |
104.17 |
2500 |
1.1726 |
0.6931 |
| 0.6622 |
108.33 |
2600 |
1.1938 |
0.7001 |
| 0.6583 |
112.5 |
2700 |
1.1832 |
0.7149 |
| 0.6299 |
116.67 |
2800 |
1.1996 |
0.7175 |
| 0.5903 |
120.83 |
2900 |
1.1986 |
0.7132 |
| 0.5816 |
125.0 |
3000 |
1.1909 |
0.7010 |
| 0.5583 |
129.17 |
3100 |
1.2079 |
0.6870 |
| 0.5392 |
133.33 |
3200 |
1.2109 |
0.7228 |
| 0.5412 |
137.5 |
3300 |
1.2353 |
0.7245 |
| 0.5136 |
141.67 |
3400 |
1.2390 |
0.7254 |
| 0.5007 |
145.83 |
3500 |
1.2273 |
0.7123 |
| 0.4883 |
150.0 |
3600 |
1.2773 |
0.7289 |
| 0.4835 |
154.17 |
3700 |
1.2678 |
0.7289 |
| 0.4568 |
158.33 |
3800 |
1.2592 |
0.7350 |
| 0.4525 |
162.5 |
3900 |
1.2705 |
0.7254 |
| 0.4379 |
166.67 |
4000 |
1.2717 |
0.7306 |
| 0.4198 |
170.83 |
4100 |
1.2618 |
0.7219 |
| 0.4216 |
175.0 |
4200 |
1.2909 |
0.7158 |
| 0.4305 |
179.17 |
4300 |
1.2808 |
0.7167 |
| 0.399 |
183.33 |
4400 |
1.2750 |
0.7193 |
| 0.3937 |
187.5 |
4500 |
1.2719 |
0.7149 |
| 0.3905 |
191.67 |
4600 |
1.2816 |
0.7158 |
| 0.3892 |
195.83 |
4700 |
1.2951 |
0.7210 |
| 0.3932 |
200.0 |
4800 |
1.2924 |
0.7201 |
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)