Downloads · 30 days
3
7% of all-time downloads
duck-hug-567/xls-r-300m-gaphon-full-v2
xls-r-300m-gaphon-full-v2 is a automatic speech recognition model from duck-hug-567. 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
3
7% of all-time downloads
All-time downloads
46
Public
Parameters
316M
29 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None 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 | Cer |
|---|---|---|---|---|
| 10.871 | 1.0 | 479 | 7.9292 | 1.0 |
| 5.007 | 2.0 | 958 | 4.3845 | 1.0 |
| 3.967 | 3.0 | 1437 | 3.9461 | 1.0 |
| 3.4433 | 4.0 | 1916 | 3.0340 | 0.8083 |
| 2.7671 | 5.0 | 2395 | 1.7773 | 0.3901 |
| 2.3127 | 6.0 | 2874 | 1.2270 | 0.2283 |
| 2.0894 | 7.0 | 3353 | 1.0236 | 0.2029 |
| 1.9395 | 8.0 | 3832 | 0.9086 | 0.1815 |
| 1.8796 | 9.0 | 4311 | 0.8445 | 0.1723 |
| 1.8544 | 10.0 | 4790 | 0.8010 | 0.1606 |
| 1.7854 | 11.0 | 5269 | 0.7699 | 0.1590 |
| 1.7562 | 12.0 | 5748 | 0.7400 | 0.1578 |
| 1.7016 | 13.0 | 6227 | 0.7248 | 0.1570 |
| 1.7283 | 14.0 | 6706 | 0.7200 | 0.1539 |
| 1.6823 | 15.0 | 7185 | 0.7071 | 0.1513 |
| 1.7002 | 16.0 | 7664 | 0.7318 | 0.1586 |
| 1.7245 | 17.0 | 8143 | 0.7316 | 0.1473 |
| 1.7978 | 18.0 | 8622 | 0.7486 | 0.1553 |
| 1.8659 | 19.0 | 9101 | 0.7891 | 0.1543 |
| 1.9872 | 20.0 | 9580 | 0.8611 | 0.1652 |
| 2.2 | 21.0 | 10059 | 1.1932 | 0.1764 |
| 2.2984 | 22.0 | 10538 | 1.1557 | 0.2086 |
| 2.3617 | 23.0 | 11017 | 1.3321 | 0.2479 |