Downloads · 30 days
48
5% of all-time downloads
KasuleTrevor/cdli-whisper-lg-sulaimank-full-a40-1e-4
cdli-whisper-lg-sulaimank-full-a40-1e-4 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
48
5% of all-time downloads
All-time downloads
901
Public
Parameters
242M
58 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt967 MB · 50%
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 |
|---|---|---|---|---|---|
| 1.5409 | 0.6775 | 250 | 1.6573 | 0.7384 | 0.4176 |
| 0.8836 | 1.3550 | 500 | 1.2932 | 0.6699 | 0.3748 |
| 0.7574 | 2.0325 | 750 | 1.2932 | 0.6090 | 0.3249 |
| 0.6354 | 2.7100 | 1000 | 1.2546 | 0.6257 | 0.3412 |
| 0.4008 | 3.3875 | 1250 | 1.4657 | 0.6404 | 0.3525 |
| 0.1993 | 4.0650 | 1500 | 1.9575 | 0.6336 | 0.3493 |
| 0.1877 | 4.7425 | 1750 | 1.9780 | 0.6467 | 0.3600 |
| 0.0928 | 5.4201 | 2000 | 2.4022 | 0.6495 | 0.3652 |
| 0.0412 | 6.0976 | 2250 | 2.7061 | 0.6543 | 0.3721 |
| 0.0415 | 6.7751 | 2500 | 2.7242 | 0.6506 | 0.3674 |
| 0.0257 | 7.4526 | 2750 | 2.8714 | 0.6573 | 0.3738 |
| 0.0122 | 8.1301 | 3000 | 2.9907 | 0.6537 | 0.3723 |
| 0.015 | 8.8076 | 3250 | 3.0586 | 0.6545 | 0.3656 |
| 0.0067 | 9.4851 | 3500 | 3.0792 | 0.6556 | 0.3694 |
| 0.0034 | 10.1626 | 3750 | 3.1344 | 0.6561 | 0.3690 |
| 0.0029 | 10.8401 | 4000 | 3.1433 | 0.6505 | 0.3701 |
| 0.0022 | 11.5176 | 4250 | 3.1614 | 0.6538 | 0.3707 |
| 0.0023 | 12.1951 | 4500 | 3.1684 | 0.6537 | 0.3681 |
| 0.0022 | 12.8726 | 4750 | 3.1748 | 0.6546 | 0.3701 |
| 0.002 | 13.5501 | 5000 | 3.1805 | 0.6545 | 0.3712 |
| 0.0021 | 14.2276 | 5250 | 3.1829 | 0.6564 | 0.3709 |
| 0.0017 | 14.9051 | 5500 | 3.1865 | 0.6564 | 0.3750 |
| 0.0021 | 15.5827 | 5750 | 3.1876 | 0.6557 | 0.3697 |
| 0.002 | 16.2602 | 6000 | 3.1888 | 0.6569 | 0.3713 |
| 0.0019 | 16.9377 | 6250 | 3.1913 | 0.6555 | 0.3694 |
| 0.002 | 17.6152 | 6500 | 3.1913 | 0.6569 | 0.3724 |
| 0.0018 | 18.2927 | 6750 | 3.1913 | 0.6583 | 0.3706 |
| 0.0019 | 18.9702 | 7000 | 3.1923 | 0.6580 | 0.3713 |
| 0.0019 | 19.6477 | 7250 | 3.1923 | 0.6553 | 0.3712 |
| 0.0019 | 20.3252 | 7500 | 3.1922 | 0.6564 | 0.3732 |
| 0.0019 | 21.0027 | 7750 | 3.1928 | 0.6551 | 0.3717 |
| 0.0018 | 21.6802 | 8000 | 3.1926 | 0.6575 | 0.3714 |
| 0.0018 | 22.3577 | 8250 | 3.1922 | 0.6577 | 0.3717 |
| 0.0019 | 23.0352 | 8500 | 3.1937 | 0.6556 | 0.3708 |
| 0.0018 | 23.7127 | 8750 | 3.1920 | 0.6571 | 0.3758 |
| 0.0017 | 24.3902 | 9000 | 3.1929 | 0.6530 | 0.3668 |
| 0.0017 | 25.0678 | 9250 | 3.1916 | 0.6537 | 0.3693 |
| 0.0019 | 25.7453 | 9500 | 3.1921 | 0.6548 | 0.3690 |
| 0.0019 | 26.4228 | 9750 | 3.1932 | 0.6559 | 0.3683 |
| 0.0017 | 27.1003 | 10000 | 3.1927 | 0.6557 | 0.3717 |