🚀 wav2vec2-base-intent-classification-ori
本模型是在 facebook/wav2vec2-base 基礎上，針對 intent-dataset 數據集進行微調得到的。它在評估集上取得了以下結果：
🚀 快速開始
此模型是基於 facebook/wav2vec2-base 微調而來，可用於特定的意圖分類任務。
📚 詳細文檔
模型描述
該模型是 wav2vec2-base 的微調版本，用於意圖分類任務。
預期用途與限制
文檔暫未提供相關信息。
訓練和評估數據
文檔暫未提供相關信息。
訓練過程
訓練超參數
訓練過程中使用了以下超參數：
- 學習率：3e-05
- 訓練批次大小：1
- 評估批次大小：1
- 隨機種子：42
- 梯度累積步數：4
- 總訓練批次大小：4
- 優化器：Adam（β1 = 0.9，β2 = 0.999，ε = 1e-08）
- 學習率調度器類型：線性
- 學習率調度器熱身比例：0.1
- 訓練輪數：45
訓練結果
| 訓練損失 |
輪數 |
步數 |
驗證損失 |
準確率 |
| 2.1867 |
1.0 |
28 |
2.1745 |
0.2708 |
| 2.1177 |
2.0 |
56 |
2.1165 |
0.2708 |
| 2.1012 |
3.0 |
84 |
2.0553 |
0.2708 |
| 1.9851 |
4.0 |
112 |
1.9551 |
0.375 |
| 1.9092 |
5.0 |
140 |
1.9765 |
0.2917 |
| 1.6848 |
6.0 |
168 |
1.8461 |
0.2917 |
| 1.6576 |
7.0 |
196 |
1.5223 |
0.5 |
| 1.4492 |
8.0 |
224 |
1.4500 |
0.4792 |
| 1.2193 |
9.0 |
252 |
1.5349 |
0.4792 |
| 1.1149 |
10.0 |
280 |
1.2159 |
0.5833 |
| 1.0615 |
11.0 |
308 |
1.1469 |
0.6875 |
| 1.0584 |
12.0 |
336 |
1.2778 |
0.6042 |
| 0.8237 |
13.0 |
364 |
1.1774 |
0.5625 |
| 0.6699 |
14.0 |
392 |
0.9661 |
0.6875 |
| 0.7414 |
15.0 |
420 |
1.2787 |
0.5208 |
| 0.5324 |
16.0 |
448 |
0.8592 |
0.7292 |
| 0.3753 |
17.0 |
476 |
0.6860 |
0.7917 |
| 0.3274 |
18.0 |
504 |
0.6210 |
0.8333 |
| 0.3667 |
19.0 |
532 |
0.7310 |
0.75 |
| 0.2347 |
20.0 |
560 |
0.6801 |
0.7292 |
| 0.2036 |
21.0 |
588 |
0.9876 |
0.6875 |
| 0.1711 |
22.0 |
616 |
0.6323 |
0.7917 |
| 0.205 |
23.0 |
644 |
0.4414 |
0.8958 |
| 0.0892 |
24.0 |
672 |
0.4253 |
0.8958 |
| 0.0777 |
25.0 |
700 |
0.4703 |
0.8958 |
| 0.0717 |
26.0 |
728 |
0.4883 |
0.8958 |
| 0.041 |
27.0 |
756 |
0.6224 |
0.8542 |
| 0.0493 |
28.0 |
784 |
0.5839 |
0.875 |
| 0.0405 |
29.0 |
812 |
0.6454 |
0.8542 |
| 0.04 |
30.0 |
840 |
0.6102 |
0.875 |
| 0.0333 |
31.0 |
868 |
0.6080 |
0.875 |
| 0.0303 |
32.0 |
896 |
0.5539 |
0.875 |
| 0.025 |
33.0 |
924 |
0.5799 |
0.8958 |
| 0.0246 |
34.0 |
952 |
0.5766 |
0.8958 |
| 0.0209 |
35.0 |
980 |
0.5700 |
0.8958 |
| 0.0225 |
36.0 |
1008 |
0.5709 |
0.8958 |
| 0.0225 |
37.0 |
1036 |
0.5582 |
0.8958 |
| 0.0217 |
38.0 |
1064 |
0.5258 |
0.875 |
| 0.0207 |
39.0 |
1092 |
0.5058 |
0.8958 |
| 0.0234 |
40.0 |
1120 |
0.4981 |
0.8958 |
| 0.021 |
41.0 |
1148 |
0.4928 |
0.9167 |
| 0.0224 |
42.0 |
1176 |
0.4962 |
0.9167 |
| 0.0212 |
43.0 |
1204 |
0.5329 |
0.8958 |
| 0.0208 |
44.0 |
1232 |
0.5727 |
0.8958 |
| 0.0206 |
45.0 |
1260 |
0.5733 |
0.8958 |
框架版本
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
📄 許可證
本項目採用 Apache-2.0 許可證。
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
PyTorch
Transformers 支持多種語言