Downloads · 30 days
5
18% of all-time downloads
alinerodrigues/wav2vec2-xlsr-1b-mecita-portuguese-all-clean-08
wav2vec2-xlsr-1b-mecita-portuguese-all-clean-08 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
5
18% of all-time downloads
All-time downloads
28
Public
Repo size
177 GB
Likes
0
Public
Click a slice to open those files.
.bin3.9 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of jonatasgrosman/wav2vec2-xls-r-1b-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 |
|---|---|---|---|---|---|
| 24.4001 | 1.0 | 67 | 2.9064 | 1.0 | 1.0 |
| 5.3927 | 2.0 | 134 | 0.7600 | 0.6051 | 0.1435 |
| 1.2383 | 3.0 | 201 | 0.1986 | 0.1251 | 0.0340 |
| 1.2383 | 4.0 | 268 | 0.1653 | 0.1000 | 0.0279 |
| 0.347 | 5.0 | 335 | 0.1546 | 0.0890 | 0.0258 |
| 0.2814 | 6.0 | 402 | 0.1446 | 0.0947 | 0.0260 |
| 0.2814 | 7.0 | 469 | 0.1518 | 0.0904 | 0.0257 |
| 0.269 | 8.0 | 536 | 0.1387 | 0.0967 | 0.0265 |
| 0.2346 | 9.0 | 603 | 0.1439 | 0.0914 | 0.0251 |
| 0.2346 | 10.0 | 670 | 0.1438 | 0.0907 | 0.0262 |
| 0.1908 | 11.0 | 737 | 0.1335 | 0.0834 | 0.0234 |
| 0.1799 | 12.0 | 804 | 0.1338 | 0.0844 | 0.0237 |
| 0.1799 | 13.0 | 871 | 0.1452 | 0.0844 | 0.0235 |
| 0.1866 | 14.0 | 938 | 0.1484 | 0.0884 | 0.0252 |
| 0.1667 | 15.0 | 1005 | 0.1518 | 0.0837 | 0.0241 |
| 0.1667 | 16.0 | 1072 | 0.1406 | 0.0857 | 0.0240 |
| 0.147 | 17.0 | 1139 | 0.1490 | 0.0857 | 0.0248 |
| 0.1476 | 18.0 | 1206 | 0.1579 | 0.0851 | 0.0250 |
| 0.1476 | 19.0 | 1273 | 0.1439 | 0.0801 | 0.0234 |
| 0.1571 | 20.0 | 1340 | 0.1484 | 0.0781 | 0.0239 |
| 0.1229 | 21.0 | 1407 | 0.1391 | 0.0755 | 0.0222 |
| 0.1229 | 22.0 | 1474 | 0.1525 | 0.0831 | 0.0244 |
| 0.1146 | 23.0 | 1541 | 0.1458 | 0.0814 | 0.0232 |
| 0.1164 | 24.0 | 1608 | 0.1453 | 0.0831 | 0.0243 |
| 0.1164 | 25.0 | 1675 | 0.1311 | 0.0811 | 0.0222 |
| 0.1145 | 26.0 | 1742 | 0.1397 | 0.0847 | 0.0247 |
| 0.0973 | 27.0 | 1809 | 0.1455 | 0.0844 | 0.0242 |
| 0.0973 | 28.0 | 1876 | 0.1395 | 0.0834 | 0.0227 |
| 0.1097 | 29.0 | 1943 | 0.1450 | 0.0821 | 0.0237 |
| 0.1072 | 30.0 | 2010 | 0.1456 | 0.0831 | 0.0237 |
| 0.1072 | 31.0 | 2077 | 0.1449 | 0.0801 | 0.0230 |
| 0.0927 | 32.0 | 2144 | 0.1637 | 0.0824 | 0.0241 |
| 0.0873 | 33.0 | 2211 | 0.1528 | 0.0828 | 0.0236 |
| 0.0873 | 34.0 | 2278 | 0.1518 | 0.0771 | 0.0230 |
| 0.0772 | 35.0 | 2345 | 0.1633 | 0.0778 | 0.0237 |
| 0.1025 | 36.0 | 2412 | 0.1462 | 0.0798 | 0.0227 |
| 0.1025 | 37.0 | 2479 | 0.1443 | 0.0781 | 0.0230 |
| 0.0919 | 38.0 | 2546 | 0.1486 | 0.0794 | 0.0230 |
| 0.0747 | 39.0 | 2613 | 0.1501 | 0.0791 | 0.0235 |
| 0.0747 | 40.0 | 2680 | 0.1596 | 0.0775 | 0.0224 |
| 0.0739 | 41.0 | 2747 | 0.1662 | 0.0811 | 0.0240 |
| 0.068 | 42.0 | 2814 | 0.1605 | 0.0808 | 0.0236 |
| 0.068 | 43.0 | 2881 | 0.1597 | 0.0788 | 0.0229 |
| 0.078 | 44.0 | 2948 | 0.1556 | 0.0765 | 0.0223 |
| 0.0656 | 45.0 | 3015 | 0.1566 | 0.0741 | 0.0218 |