Downloads · 30 days
3
8% of all-time downloads
charlesfrye/ap-vHLaj4AuIgw86bx1KZb38G
ap-vHLaj4AuIgw86bx1KZb38G is a automatic speech recognition model from charlesfrye. 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
8% of all-time downloads
All-time downloads
39
Public
Parameters
1.5B
61.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-large-v3 on the None 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 | Model Preparation Time | Wer |
|---|---|---|---|---|---|
| 0.3828 | 0.9791 | 41 | 0.3761 | 0.022 | 0.1424 |
| 0.2079 | 1.9791 | 82 | 0.3005 | 0.022 | 0.1094 |
| 0.1434 | 2.9791 | 123 | 0.3007 | 0.022 | 0.1087 |
| 0.0763 | 3.9791 | 164 | 0.3298 | 0.022 | 0.1120 |
| 0.0564 | 4.9791 | 205 | 0.3544 | 0.022 | 0.1250 |
| 0.0305 | 5.9791 | 246 | 0.4075 | 0.022 | 0.1194 |
| 0.0319 | 6.9791 | 287 | 0.3782 | 0.022 | 0.1212 |
| 0.0244 | 7.9791 | 328 | 0.4193 | 0.022 | 0.1097 |
| 0.0212 | 8.9791 | 369 | 0.4446 | 0.022 | 0.1226 |
| 0.0202 | 9.9791 | 410 | 0.4343 | 0.022 | 0.1096 |