Downloads · 30 days
18
7% of all-time downloads
KasuleTrevor/cdli-whisper-lg-sulaimank-encoder-a40-1e-4-polynomial-5k
cdli-whisper-lg-sulaimank-encoder-a40-1e-4-polynomial-5k is a automatic speech recognition model from KasuleTrevor. 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
18
7% of all-time downloads
All-time downloads
256
Public
Parameters
242M
8.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors967 MB · 73%
From the Hugging Face model README
This model is a fine-tuned version of sulaimank/whisper-small-luganda-400hrs 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 | Cer |
|---|---|---|---|---|---|
| 1.3144 | 0.6784 | 500 | 1.5432 | 0.6927 | 0.3899 |
| 0.9824 | 1.3569 | 1000 | 1.4118 | 0.6656 | 0.3669 |
| 0.8289 | 2.0353 | 1500 | 1.3816 | 0.6534 | 0.3512 |
| 0.9775 | 2.7137 | 2000 | 1.3905 | 0.6655 | 0.3607 |
| 0.7458 | 3.3921 | 2500 | 1.4161 | 0.6630 | 0.3573 |
| 0.7503 | 4.0706 | 3000 | 1.4458 | 0.6591 | 0.3535 |
| 0.7465 | 4.7490 | 3500 | 1.4585 | 0.6629 | 0.3638 |
| 0.6613 | 5.4274 | 4000 | 1.4748 | 0.6582 | 0.3574 |
| 0.7178 | 6.1058 | 4500 | 1.4737 | 0.6591 | 0.3611 |
| 0.6366 | 6.7843 | 5000 | 1.4773 | 0.6581 | 0.3593 |