Downloads · 30 days
30
5% of all-time downloads
DrishtiSharma/wav2vec2-xls-r-pa-IN-a1
wav2vec2-xls-r-pa-IN-a1 is a automatic speech recognition model from DrishtiSharma. 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
30
5% of all-time downloads
All-time downloads
596
Public
Repo size
29 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - PA-IN 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 |
|---|---|---|---|---|
| 3.5841 | 9.26 | 500 | 3.2514 | 0.9941 |
| 0.3992 | 18.52 | 1000 | 0.8790 | 0.6107 |
| 0.2409 | 27.78 | 1500 | 1.0012 | 0.6366 |
| 0.1447 | 37.04 | 2000 | 1.0167 | 0.6276 |
| 0.1109 | 46.3 | 2500 | 1.0638 | 0.5653 |
| 0.0797 | 55.56 | 3000 | 1.1447 | 0.5715 |
| 0.0636 | 64.81 | 3500 | 1.1503 | 0.5316 |
| 0.0466 | 74.07 | 4000 | 1.2227 | 0.5386 |
| 0.0372 | 83.33 | 4500 | 1.1214 | 0.5225 |
| 0.0239 | 92.59 | 5000 | 1.1375 | 0.4998 |