Downloads · 30 days
3
17% of all-time downloads
Youssef1234/whisper-base-specAug-non
whisper-base-specAug-non is a automatic speech recognition model from Youssef1234. 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
17% of all-time downloads
All-time downloads
18
Public
Parameters
72.6M
1.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors290 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of Youssef1234/whisper-base-specAug 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 | Wer |
|---|---|---|---|---|
| 0.208 | 0.25 | 239 | 0.3320 | 15.8293 |
| 0.1384 | 0.5 | 478 | 0.3435 | 17.0993 |
| 0.109 | 0.75 | 717 | 0.3537 | 17.1040 |