Downloads · 30 days
7
25% of all-time downloads
duck-hug-567/xls-r-300m-gaphon-full
xls-r-300m-gaphon-full 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
7
25% of all-time downloads
All-time downloads
28
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 |
|---|---|---|---|---|
| 9.9885 | 1.0 | 479 | 7.5339 | 1.0 |
| 4.8097 | 2.0 | 958 | 4.2202 | 1.0 |
| 3.5846 | 3.0 | 1437 | 3.5106 | 0.9380 |
| 3.2018 | 4.0 | 1916 | 2.9622 | 0.7637 |
| 2.6441 | 5.0 | 2395 | 1.8222 | 0.4120 |
| 2.2188 | 6.0 | 2874 | 1.2525 | 0.2557 |
| 1.9679 | 7.0 | 3353 | 1.0033 | 0.2065 |
| 1.8208 | 8.0 | 3832 | 0.9032 | 0.2027 |
| 1.7499 | 9.0 | 4311 | 0.8297 | 0.1907 |
| 1.7361 | 10.0 | 4790 | 0.7933 | 0.1816 |
| 1.6762 | 11.0 | 5269 | 0.7609 | 0.1784 |
| 1.6502 | 12.0 | 5748 | 0.7439 | 0.1746 |
| 1.5921 | 13.0 | 6227 | 0.7156 | 0.1746 |
| 1.6082 | 14.0 | 6706 | 0.7112 | 0.1694 |
| 1.5883 | 15.0 | 7185 | 0.7024 | 0.1683 |
| 1.583 | 16.0 | 7664 | 0.7203 | 0.1701 |
| 1.6126 | 17.0 | 8143 | 0.7343 | 0.1643 |
| 1.7458 | 18.0 | 8622 | 0.8694 | 0.1673 |
| 1.7716 | 19.0 | 9101 | 0.8967 | 0.1700 |
| 1.9119 | 20.0 | 9580 | 1.0167 | 0.1809 |
| 2.1044 | 21.0 | 10059 | 1.2569 | 0.2012 |
| 2.3158 | 22.0 | 10538 | 1.5060 | 0.2399 |
| 2.1031 | 23.0 | 11017 | 1.2085 | 0.2533 |