Downloads · 30 days
8
26% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-hindi-iv_hindi_only-62080-normalized-alldata-1e-4-epochs-100-FT
wav2vec2-large-xlsr-hindi-iv_hindi_only-62080-normalized-alldata-1e-4-epochs-100-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
8
26% of all-time downloads
All-time downloads
31
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 skylord/wav2vec2-large-xlsr-hindi 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 |
|---|---|---|---|---|
| 11.2410 | 1.0 | 540 | 1.0760 | 52.4930 |
| 2.3583 | 2.0 | 1080 | 0.7608 | 41.5263 |
| 1.8888 | 3.0 | 1620 | 0.7006 | 37.7075 |
| 1.7042 | 4.0 | 2160 | 0.6716 | 35.6657 |
| 1.5425 | 5.0 | 2700 | 0.6651 | 34.7572 |
| 1.4556 | 6.0 | 3240 | 0.6510 | 33.3405 |
| 1.3716 | 7.0 | 3780 | 0.6235 | 32.9556 |
| 1.2901 | 8.0 | 4320 | 0.6484 | 32.4967 |
| 1.2281 | 9.0 | 4860 | 0.6315 | 33.5037 |
| 1.2347 | 10.0 | 5400 | 0.6388 | 33.1742 |
| 1.1978 | 11.0 | 5940 | 0.6956 | 34.6278 |