Downloads · 30 days
4
2% of all-time downloads
lishantKarki/wav2vec2-large-xls-r-300m-nepali-openslr1
wav2vec2-large-xls-r-300m-nepali-openslr1 is a automatic speech recognition model from lishantKarki. 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
4
2% of all-time downloads
All-time downloads
209
Public
Parameters
316M
25.2 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 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 |
|---|---|---|---|---|
| 8.7477 | 1.0 | 250 | 4.2372 | 1.0 |
| 7.1590 | 2.0 | 500 | 3.5656 | 1.0 |
| 6.8443 | 3.0 | 750 | 3.4126 | 0.9996 |
| 3.1266 | 4.0 | 1000 | 1.0861 | 0.8784 |
| 2.3259 | 5.0 | 1250 | 0.7286 | 0.7456 |
| 2.0140 | 6.0 | 1500 | 0.5923 | 0.6495 |
| 1.8487 | 7.0 | 1750 | 0.5320 | 0.5922 |
| 1.6802 | 8.0 | 2000 | 0.4915 | 0.5717 |
| 1.5725 | 9.0 | 2250 | 0.4750 | 0.5544 |
| 1.6048 | 10.0 | 2500 | 0.4665 | 0.5314 |