Downloads · 30 days
22
31% of all-time downloads
davidilag/wav2vec2-xls-r-1b-scandinavian-E4-100h-30-epochs-20250205_v1
wav2vec2-xls-r-1b-scandinavian-E4-100h-30-epochs-20250205_v1 is a automatic speech recognition model from davidilag. 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
22
31% of all-time downloads
All-time downloads
70
Public
Parameters
963M
27 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.9 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the npsc 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 |
|---|---|---|---|---|---|
| 1.2049 | 0.8937 | 1000 | 0.4634 | 39.6343 | 10.8827 |
| 0.3474 | 1.7873 | 2000 | 0.2548 | 22.5268 | 6.2312 |
| 0.5268 | 2.6810 | 3000 | 0.2442 | 21.1395 | 5.8260 |
| 0.3613 | 3.5746 | 4000 | 0.2249 | 21.5062 | 5.9399 |
| 0.286 | 4.4683 | 5000 | 0.2420 | 20.2775 | 5.6564 |
| 0.4378 | 5.3619 | 6000 | 0.2170 | 20.1901 | 5.5473 |
| 0.2343 | 6.2556 | 7000 | 0.2105 | 19.6430 | 5.4665 |
| 0.3844 | 7.1492 | 8000 | 0.2274 | 19.4775 | 5.4022 |
| 0.3825 | 8.0429 | 9000 | 0.2781 | 21.6855 | 5.8483 |
| 0.6298 | 8.9366 | 10000 | 0.4738 | 23.4739 | 6.2581 |
| 0.9835 | 9.8302 | 11000 | 0.8216 | 56.0716 | 16.6136 |
| 1.182 | 10.7239 | 12000 | 0.9427 | 96.6024 | 42.1068 |
| 1.3679 | 11.6175 | 13000 | 1.0725 | 97.0622 | 46.8494 |
| 1.7475 | 12.5112 | 14000 | 1.1562 | 88.7740 | 40.7348 |
| 1.9869 | 13.4048 | 15000 | 1.2288 | 90.1590 | 47.7102 |
| 1.6371 | 14.2985 | 16000 | 1.0844 | 87.0683 | 39.4960 |
| 1.8 | 15.1921 | 17000 | 1.0171 | 73.3078 | 28.2554 |
| 1.8107 | 16.0858 | 18000 | 1.2218 | 82.6006 | 41.2784 |
| 1.7956 | 16.9794 | 19000 | 1.1893 | 81.6880 | 39.3608 |
| 1.5845 | 17.8731 | 20000 | 1.1725 | 74.1354 | 30.8995 |
| 2.093 | 18.7668 | 21000 | 1.1438 | 75.8790 | 32.5999 |
| 1.727 | 19.6604 | 22000 | 1.1820 | 69.9734 | 26.9008 |
| 1.8911 | 20.5541 | 23000 | 1.2419 | 66.2931 | 23.6298 |
| 2.1902 | 21.4477 | 24000 | 1.2287 | 67.1448 | 24.5529 |
| 1.656 | 22.3414 | 25000 | 1.3334 | 69.3011 | 24.5272 |
| 2.0719 | 23.2350 | 26000 | 1.3242 | 69.8735 | 24.7654 |
| 1.8138 | 24.1287 | 27000 | 1.3185 | 69.8079 | 24.6849 |
| 1.6938 | 25.0223 | 28000 | 1.3157 | 71.7401 | 25.6867 |
| 1.8782 | 25.9160 | 29000 | 1.3222 | 84.3741 | 32.2539 |
| 2.0728 | 26.8097 | 30000 | 1.3545 | 92.6014 | 37.9307 |
| 1.8867 | 27.7033 | 31000 | 1.3746 | 94.0979 | 39.0716 |
| 2.3103 | 28.5970 | 32000 | 1.3817 | 94.8795 | 39.9214 |
| 2.2009 | 29.4906 | 33000 | 1.3819 | 94.9209 | 39.9728 |