Downloads · 30 days
7
6% of all-time downloads
cantillation/whisper-medium-he-teamim-aviv-bavly-without-nikud-8000-steps-lr-1e-5
whisper-medium-he-teamim-aviv-bavly-without-nikud-8000-steps-lr-1e-5 is a automatic speech recognition model from cantillation. 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
7
6% of all-time downloads
All-time downloads
112
Public
Parameters
764M
12.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.1 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-medium 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 | Precision | Recall | F1 | Precision Median | Recall Median | F1 Median | Precision Max | Recall Max | F1 Max | Precision Min | Recall Min | F1 Min |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0675 | 0.4 | 1000 | 0.1219 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 0.0313 | 0.79 | 2000 | 0.1256 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 0.0262 | 1.19 | 3000 | 0.1282 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 0.0063 | 1.58 | 4000 | 0.1273 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 0.0073 | 1.98 | 5000 | 0.1299 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 0.0024 | 2.37 | 6000 | 0.1337 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 0.0014 | 2.77 | 7000 | 0.1375 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| 0.0002 | 3.17 | 8000 | 0.1370 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0 | 0 | 0 | 0 | 0 | 0 |