语言:
- 葡萄牙语(pt)
许可证: Apache-2.0
标签:
- 自动语音识别
- Mozilla基金会/common_voice_7_0数据集
- 基于训练器生成
- 葡萄牙语(pt)
数据集:
- Mozilla基金会/common_voice_7_0
模型索引:
- 名称: wavlm-large-CORAA-pt-cv7
结果: []
wavlm-large-CORAA-pt-cv7
该模型是基于lgris/WavLM-large-CORAA-pt在common_voice数据集上微调的版本。在评估集上取得了以下结果：
- 损失值: 0.2546
- 词错误率(WER): 0.2261
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: 0.0001
- 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 (β1=0.9, β2=0.999, ε=1e-08)
- 学习率调度器类型: 线性
- 学习率预热步数: 100
- 总训练步数: 5000
训练结果
| 训练损失 |
周期 |
步数 |
验证损失 |
词错误率 |
| 0.6029 |
0.13 |
100 |
0.3679 |
0.3347 |
| 0.5297 |
0.26 |
200 |
0.3516 |
0.3227 |
| 0.5134 |
0.39 |
300 |
0.3327 |
0.3167 |
| 0.4941 |
0.52 |
400 |
0.3281 |
0.3122 |
| 0.4816 |
0.65 |
500 |
0.3154 |
0.3102 |
| 0.4649 |
0.78 |
600 |
0.3199 |
0.3058 |
| 0.461 |
0.91 |
700 |
0.3047 |
0.2974 |
| 0.4613 |
1.04 |
800 |
0.3006 |
0.2900 |
| 0.4198 |
1.17 |
900 |
0.2951 |
0.2891 |
| 0.3864 |
1.3 |
1000 |
0.2989 |
0.2862 |
| 0.3963 |
1.43 |
1100 |
0.2932 |
0.2830 |
| 0.3953 |
1.56 |
1200 |
0.2936 |
0.2829 |
| 0.3962 |
1.69 |
1300 |
0.2952 |
0.2773 |
| 0.3811 |
1.82 |
1400 |
0.2915 |
0.2748 |
| 0.3736 |
1.95 |
1500 |
0.2839 |
0.2684 |
| 0.3507 |
2.08 |
1600 |
0.2914 |
0.2678 |
| 0.3277 |
2.21 |
1700 |
0.2895 |
0.2652 |
| 0.3344 |
2.34 |
1800 |
0.2843 |
0.2673 |
| 0.335 |
2.47 |
1900 |
0.2821 |
0.2635 |
| 0.3559 |
2.6 |
2000 |
0.2830 |
0.2599 |
| 0.3254 |
2.73 |
2100 |
0.2711 |
0.2577 |
| 0.3263 |
2.86 |
2200 |
0.2685 |
0.2546 |
| 0.3266 |
2.99 |
2300 |
0.2679 |
0.2521 |
| 0.3066 |
3.12 |
2400 |
0.2727 |
0.2526 |
| 0.2998 |
3.25 |
2500 |
0.2648 |
0.2537 |
| 0.2961 |
3.38 |
2600 |
0.2630 |
0.2519 |
| 0.3046 |
3.51 |
2700 |
0.2684 |
0.2506 |
| 0.3006 |
3.64 |
2800 |
0.2604 |
0.2492 |
| 0.2992 |
3.77 |
2900 |
0.2682 |
0.2508 |
| 0.2775 |
3.9 |
3000 |
0.2732 |
0.2440 |
| 0.2903 |
4.03 |
3100 |
0.2659 |
0.2427 |
| 0.2535 |
4.16 |
3200 |
0.2650 |
0.2433 |
| 0.2714 |
4.29 |
3300 |
0.2588 |
0.2394 |
| 0.2636 |
4.42 |
3400 |
0.2652 |
0.2434 |
| 0.2647 |
4.55 |
3500 |
0.2624 |
0.2371 |
| 0.2796 |
4.67 |
3600 |
0.2611 |
0.2373 |
| 0.2644 |
4.8 |
3700 |
0.2604 |
0.2341 |
| 0.2657 |
4.93 |
3800 |
0.2567 |
0.2331 |
| 0.2423 |
5.06 |
3900 |
0.2594 |
0.2322 |
| 0.2556 |
5.19 |
4000 |
0.2587 |
0.2323 |
| 0.2327 |
5.32 |
4100 |
0.2639 |
0.2299 |
| 0.2613 |
5.45 |
4200 |
0.2569 |
0.2310 |
| 0.2382 |
5.58 |
4300 |
0.2585 |
0.2298 |
| 0.2404 |
5.71 |
4400 |
0.2543 |
0.2287 |
| 0.2368 |
5.84 |
4500 |
0.2553 |
0.2286 |
| 0.2514 |
5.97 |
4600 |
0.2517 |
0.2279 |
| 0.2415 |
6.1 |
4700 |
0.2524 |
0.2270 |
| 0.2338 |
6.23 |
4800 |
0.2540 |
0.2265 |
| 0.219 |
6.36 |
4900 |
0.2549 |
0.2263 |
| 0.2428 |
6.49 |
5000 |
0.2546 |
0.2261 |
框架版本
- Transformers 4.16.1
- PyTorch 1.10.0+cu111
- Datasets 1.18.2
- 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)