Downloads · 30 days
3
2% of all-time downloads
wandererupak/whisper-small-n-demo-ultimate-train-XX
whisper-small-n-demo-ultimate-train-XX is a automatic speech recognition model from wandererupak. 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
3
2% of all-time downloads
All-time downloads
126
Public
Parameters
242M
27.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt1.9 GB · 50%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-small on the N Demo Final 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 | Cer |
|---|---|---|---|---|---|
| 1.1809 | 0.9965 | 285 | 0.5577 | 71.1024 | 26.9361 |
| 0.8395 | 1.9930 | 570 | 0.4625 | 61.6929 | 22.6497 |
| 0.5538 | 2.9895 | 855 | 0.4426 | 58.7402 | 23.2476 |
| 0.3483 | 3.9860 | 1140 | 0.4445 | 53.3858 | 20.1354 |
| 0.1779 | 4.9825 | 1425 | 0.4912 | 52.9528 | 18.9396 |
| 0.0815 | 5.9790 | 1710 | 0.5356 | 52.3622 | 18.8171 |
| 0.0273 | 6.9755 | 1995 | 0.5762 | 51.8504 | 18.7306 |
| 0.0131 | 7.9720 | 2280 | 0.6149 | 51.8110 | 18.7234 |
| 0.0049 | 8.9685 | 2565 | 0.6370 | 51.4173 | 18.6298 |
| 0.0044 | 9.9650 | 2850 | 0.6409 | 51.5748 | 18.7090 |