Downloads · 30 days
3
1% of all-time downloads
duck-hug-567/xls-r-300m-eng-irish-combined-v2
xls-r-300m-eng-irish-combined-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
1% of all-time downloads
All-time downloads
238
Public
Parameters
316M
20.2 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 | Cer | Validation Loss |
|---|---|---|---|---|
| 1.6361 | 1.0 | 7654 | 0.2478 | 0.9175 |
| 1.4082 | 2.0 | 15308 | 0.1918 | 0.5791 |
| 1.2803 | 3.0 | 22962 | 0.1801 | 0.5201 |
| 1.1649 | 4.0 | 30616 | 0.1774 | 0.4900 |
| 1.081 | 5.0 | 38270 | 0.1667 | 0.4769 |
| 1.0157 | 6.0 | 45924 | 0.1656 | 0.4627 |
| 1.1126 | 7.0 | 53578 | 0.1716 | 0.4498 |
| 1.0686 | 8.0 | 61232 | 0.1678 | 0.4531 |
| 0.9781 | 9.0 | 68886 | 0.1552 | 0.4485 |
| 0.9737 | 10.0 | 76540 | 0.1596 | 0.4460 |
| 0.9293 | 11.0 | 84194 | 0.4328 | 0.1684 |
| 0.8585 | 12.0 | 91848 | 0.4376 | 0.1665 |
| 0.8525 | 13.0 | 99502 | 0.4496 | 0.1671 |
| 0.9282 | 14.0 | 107156 | 0.4522 | 0.1645 |
| 0.8537 | 15.0 | 114810 | 0.4488 | 0.1646 |
| 0.7725 | 16.0 | 122464 | 0.4719 | 0.1588 |