Downloads · 30 days
4
17% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-mucs-62026-hinglish_mixed_scripts-45_100-1e-4-epochs-50-FT
wav2vec2-large-xlsr-53-mucs-62026-hinglish_mixed_scripts-45_100-1e-4-epochs-50-FT is a automatic speech recognition model from dianavdavidson. 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
17% of all-time downloads
All-time downloads
24
Public
Parameters
316M
1.3 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-large-xlsr-53 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 | Global Wer |
|---|---|---|---|---|
| No log | 1.0 | 302 | 3.7156 | 100.0 |
| 18.2511 | 2.0 | 604 | 3.4026 | 100.0 |
| 18.2511 | 3.0 | 906 | 1.9441 | 80.8778 |
| 5.7894 | 4.0 | 1208 | 1.0001 | 46.0361 |
| 2.0437 | 5.0 | 1510 | 0.8404 | 35.8625 |
| 2.0437 | 6.0 | 1812 | 0.8262 | 29.6870 |
| 1.1784 | 7.0 | 2114 | 0.8068 | 28.8534 |
| 1.1784 | 8.0 | 2416 | 0.8104 | 28.5131 |
| 0.8609 | 9.0 | 2718 | 0.8219 | 27.2712 |
| 0.6667 | 10.0 | 3020 | 0.8187 | 25.4338 |
| 0.6667 | 11.0 | 3322 | 0.7978 | 24.9234 |
| 0.5034 | 12.0 | 3624 | 0.8525 | 25.3998 |
| 0.5034 | 13.0 | 3926 | 0.8577 | 25.0255 |
| 0.4246 | 14.0 | 4228 | 0.8949 | 24.9234 |