Downloads · 30 days
6
22% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-mucs-61965-hinglish_mixed_scripts-30_70-1e-4-steps-12000-FT
wav2vec2-large-xlsr-53-mucs-61965-hinglish_mixed_scripts-30_70-1e-4-steps-12000-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
6
22% of all-time downloads
All-time downloads
27
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 |
|---|---|---|---|---|
| 4.7555 | 0.4475 | 1000 | 1.8054 | 75.9578 |
| 2.0155 | 0.8951 | 2000 | 1.0101 | 40.7458 |
| 1.5857 | 1.3424 | 3000 | 0.8682 | 34.9225 |
| 1.4342 | 1.7899 | 4000 | 0.8077 | 31.1766 |
| 1.1248 | 2.2372 | 5000 | 0.7942 | 30.1124 |
| 1.2233 | 2.6847 | 6000 | 0.7634 | 28.3756 |
| 0.9035 | 3.1320 | 7000 | 0.7583 | 27.9585 |
| 0.9446 | 3.5795 | 8000 | 0.7361 | 26.7666 |
| 0.9083 | 4.0269 | 9000 | 0.7591 | 26.2983 |
| 0.7494 | 4.4744 | 10000 | 0.7280 | 25.1830 |
| 0.7541 | 4.9219 | 11000 | 0.7197 | 24.9191 |
| 0.5984 | 5.3692 | 12000 | 0.7095 | 25.0894 |