Downloads · 30 days
5
7% of all-time downloads
thevan2404/whisper-medium-ft-13epochs-movie
whisper-medium-ft-13epochs-movie is a automatic speech recognition model from thevan2404. 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
5
7% of all-time downloads
All-time downloads
70
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.en 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 |
|---|---|---|---|---|
| 0.5434 | 1.0 | 1424 | 0.5275 | 19.9446 |
| 0.4534 | 2.0 | 2848 | 0.5253 | 22.0473 |
| 0.3595 | 3.0 | 4272 | 0.5482 | 22.1733 |
| 0.2799 | 4.0 | 5696 | 0.6103 | 21.2478 |
| 0.2167 | 5.0 | 7120 | 0.6925 | 22.3684 |
| 0.1551 | 6.0 | 8544 | 0.7764 | 23.7409 |
| 0.108 | 7.0 | 9968 | 0.8426 | 22.6265 |
| 0.0711 | 8.0 | 11392 | 0.9081 | 23.9927 |
| 0.0428 | 9.0 | 12816 | 0.9621 | 22.8532 |
| 0.0272 | 10.0 | 14240 | 1.0026 | 22.7084 |
| 0.0242 | 11.0 | 15664 | 1.0401 | 23.5331 |
| 0.0166 | 12.0 | 17088 | 1.0614 | 22.7902 |
| 0.0104 | 13.0 | 18512 | 1.0875 | 23.5961 |