Downloads · 30 days
7
16% of all-time downloads
alinerodrigues/wav2vec2-large-xlsr-mecita-coraa-portuguese-2-all-clean-04
wav2vec2-large-xlsr-mecita-coraa-portuguese-2-all-clean-04 is a automatic speech recognition model from alinerodrigues. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
7
16% of all-time downloads
All-time downloads
44
Public
Repo size
77 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of Edresson/wav2vec2-large-xlsr-coraa-portuguese on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 21.443 | 1.0 | 67 | 3.3855 | 1.0 | 1.0 |
| 7.6266 | 2.0 | 134 | 2.9888 | 1.0 | 1.0 |
| 3.0287 | 3.0 | 201 | 2.9185 | 1.0 | 1.0 |
| 3.0287 | 4.0 | 268 | 2.9032 | 1.0 | 1.0 |
| 2.9145 | 5.0 | 335 | 2.9048 | 1.0 | 1.0 |
| 2.9023 | 6.0 | 402 | 2.8616 | 1.0 | 1.0 |
| 2.9023 | 7.0 | 469 | 2.5183 | 0.9993 | 0.9994 |
| 2.6984 | 8.0 | 536 | 1.0592 | 0.9114 | 0.2155 |
| 1.3929 | 9.0 | 603 | 0.5084 | 0.2198 | 0.0598 |
| 1.3929 | 10.0 | 670 | 0.3810 | 0.1796 | 0.0503 |
| 0.7134 | 11.0 | 737 | 0.3273 | 0.1708 | 0.0464 |
| 0.533 | 12.0 | 804 | 0.2878 | 0.1559 | 0.0426 |
| 0.533 | 13.0 | 871 | 0.2657 | 0.1366 | 0.0397 |
| 0.4293 | 14.0 | 938 | 0.2464 | 0.1373 | 0.0389 |
| 0.3677 | 15.0 | 1005 | 0.2382 | 0.1282 | 0.0365 |
| 0.3677 | 16.0 | 1072 | 0.2263 | 0.1251 | 0.0357 |
| 0.3445 | 17.0 | 1139 | 0.2220 | 0.1194 | 0.0344 |
| 0.3056 | 18.0 | 1206 | 0.2189 | 0.1113 | 0.0342 |
| 0.3056 | 19.0 | 1273 | 0.2099 | 0.1082 | 0.0329 |
| 0.3111 | 20.0 | 1340 | 0.2049 | 0.1048 | 0.0326 |
| 0.259 | 21.0 | 1407 | 0.2105 | 0.1008 | 0.0317 |
| 0.259 | 22.0 | 1474 | 0.2059 | 0.0971 | 0.0311 |
| 0.2515 | 23.0 | 1541 | 0.2052 | 0.0971 | 0.0312 |
| 0.2379 | 24.0 | 1608 | 0.1989 | 0.0933 | 0.0303 |
| 0.2379 | 25.0 | 1675 | 0.1990 | 0.0933 | 0.0305 |
| 0.2208 | 26.0 | 1742 | 0.1951 | 0.1001 | 0.0310 |
| 0.2347 | 27.0 | 1809 | 0.1903 | 0.0913 | 0.0294 |
| 0.2347 | 28.0 | 1876 | 0.1904 | 0.0930 | 0.0299 |
| 0.2204 | 29.0 | 1943 | 0.1882 | 0.0927 | 0.0300 |
| 0.206 | 30.0 | 2010 | 0.1875 | 0.0923 | 0.0296 |
| 0.206 | 31.0 | 2077 | 0.1802 | 0.0944 | 0.0300 |
| 0.1948 | 32.0 | 2144 | 0.1743 | 0.0960 | 0.0299 |
| 0.1955 | 33.0 | 2211 | 0.1825 | 0.0900 | 0.0296 |
| 0.1955 | 34.0 | 2278 | 0.1798 | 0.0893 | 0.0292 |
| 0.1752 | 35.0 | 2345 | 0.1765 | 0.0896 | 0.0291 |
| 0.1781 | 36.0 | 2412 | 0.1733 | 0.0866 | 0.0282 |
| 0.1781 | 37.0 | 2479 | 0.1761 | 0.0893 | 0.0292 |
| 0.1851 | 38.0 | 2546 | 0.1781 | 0.0879 | 0.0286 |
| 0.1904 | 39.0 | 2613 | 0.1751 | 0.0883 | 0.0283 |
| 0.1904 | 40.0 | 2680 | 0.1724 | 0.0883 | 0.0281 |
| 0.1691 | 41.0 | 2747 | 0.1785 | 0.0906 | 0.0285 |
| 0.1715 | 42.0 | 2814 | 0.1791 | 0.0889 | 0.0288 |
| 0.1715 | 43.0 | 2881 | 0.1817 | 0.0856 | 0.0277 |
| 0.1441 | 44.0 | 2948 | 0.1765 | 0.0852 | 0.0280 |
| 0.1542 | 45.0 | 3015 | 0.1797 | 0.0873 | 0.0292 |
| 0.1542 | 46.0 | 3082 | 0.1827 | 0.0856 | 0.0285 |
| 0.1543 | 47.0 | 3149 | 0.1798 | 0.0839 | 0.0284 |
| 0.1454 | 48.0 | 3216 | 0.1756 | 0.0862 | 0.0284 |
| 0.1454 | 49.0 | 3283 | 0.1740 | 0.0866 | 0.0280 |
| 0.1447 | 50.0 | 3350 | 0.1736 | 0.0893 | 0.0285 |
| 0.1425 | 51.0 | 3417 | 0.1742 | 0.0883 | 0.0283 |
| 0.1425 | 52.0 | 3484 | 0.1771 | 0.0876 | 0.0286 |
| 0.1431 | 53.0 | 3551 | 0.1765 | 0.0910 | 0.0288 |
| 0.1386 | 54.0 | 3618 | 0.1784 | 0.0862 | 0.0289 |
| 0.1386 | 55.0 | 3685 | 0.1775 | 0.0910 | 0.0291 |
| 0.133 | 56.0 | 3752 | 0.1796 | 0.0859 | 0.0279 |
| 0.137 | 57.0 | 3819 | 0.1766 | 0.0879 | 0.0283 |
| 0.137 | 58.0 | 3886 | 0.1775 | 0.0876 | 0.0284 |
| 0.1324 | 59.0 | 3953 | 0.1783 | 0.0876 | 0.0285 |
| 0.1393 | 60.0 | 4020 | 0.1822 | 0.0835 | 0.0275 |