Downloads · 30 days
103
82% of all-time downloads
wiekeharmsen/whisper-small-dart-100cor
whisper-small-dart-100cor is a automatic speech recognition model from wiekeharmsen. 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
103
82% of all-time downloads
All-time downloads
126
Public
Parameters
242M
4.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors967 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 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 |
|---|---|---|---|---|
| 0.0001 | 100.0 | 1000 | 3.7327 | 59.7838 |
| 0.0 | 200.0 | 2000 | 4.0011 | 60.5405 |
| 0.0 | 300.0 | 3000 | 4.2211 | 59.6216 |
| 0.0 | 400.0 | 4000 | 4.4124 | 64.9730 |
| 0.0 | 500.0 | 5000 | 4.4754 | 64.3243 |