Downloads · 30 days
4
13% of all-time downloads
thevan2404/whisper-medium-mini-media-long-ft-10epochs
whisper-medium-mini-media-long-ft-10epochs 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
4
13% of all-time downloads
All-time downloads
30
Public
Parameters
764M
30.6 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 |
|---|---|---|---|---|
| 0.3376 | 1.0 | 532 | 0.3209 | 4.3127 |
| 0.1659 | 2.0 | 1064 | 0.3037 | 5.0161 |
| 0.0529 | 3.0 | 1596 | 0.3163 | 4.2894 |
| 0.0144 | 4.0 | 2128 | 0.3405 | 3.8264 |
| 0.0085 | 5.0 | 2660 | 0.3296 | 3.9309 |
| 0.0037 | 6.0 | 3192 | 0.3362 | 4.1423 |
| 0.0037 | 7.0 | 3724 | 0.3391 | 4.0659 |
| 0.0023 | 8.0 | 4256 | 0.3458 | 3.8939 |
| 0.0015 | 9.0 | 4788 | 0.3493 | 3.9204 |
| 0.0008 | 10.0 | 5320 | 0.3509 | 4.0732 |