Downloads · 30 days
66
0% of all-time downloads
sam8000/whisper-large-v3-turbo-maltese-malta
whisper-large-v3-turbo-maltese-malta is a automatic speech recognition model from sam8000. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
66
0% of all-time downloads
All-time downloads
55.5K
Public
Parameters
809M
80.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the fleurs 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 | Model Preparation Time | Wer Ortho | Wer |
|---|---|---|---|---|---|---|
| 0.8035 | 0.1170 | 32 | 0.8262 | 0.0067 | 59.6043 | 39.5151 |
| 0.4214 | 0.2340 | 64 | 0.6413 | 0.0067 | 48.4838 | 25.9491 |
| 0.3364 | 0.3510 | 96 | 0.5759 | 0.0067 | 45.7317 | 22.1842 |
| 0.2865 | 0.4680 | 128 | 0.5396 | 0.0067 | 44.8798 | 21.5635 |
| 0.2636 | 0.5850 | 160 | 0.5267 | 0.0067 | 43.1983 | 19.7733 |
| 0.2484 | 0.7020 | 192 | 0.4909 | 0.0067 | 42.6321 | 18.4914 |
| 0.2494 | 0.8190 | 224 | 0.4828 | 0.0067 | 42.1669 | 18.3834 |
| 0.2348 | 0.9360 | 256 | 0.4829 | 0.0067 | 42.0380 | 17.7132 |
| 0.1985 | 1.0512 | 288 | 0.4681 | 0.0067 | 40.7040 | 17.4883 |
| 0.1884 | 1.1682 | 320 | 0.4705 | 0.0067 | 41.2757 | 16.9800 |
| 0.1878 | 1.2852 | 352 | 0.4599 | 0.0067 | 40.6928 | 16.3908 |
| 0.1856 | 1.4022 | 384 | 0.4641 | 0.0067 | 41.2869 | 16.7461 |
| 0.1873 | 1.5192 | 416 | 0.4506 | 0.0067 | 41.2813 | 15.8645 |
| 0.1795 | 1.6362 | 448 | 0.4634 | 0.0067 | 40.5190 | 16.5122 |
| 0.1802 | 1.7532 | 480 | 0.4758 | 0.0067 | 40.5358 | 16.0175 |
| 0.1782 | 1.8702 | 512 | 0.4512 | 0.0067 | 40.2388 | 15.7566 |
| 0.1785 | 1.9872 | 544 | 0.4510 | 0.0067 | 40.0706 | 15.4777 |
| 0.1503 | 2.1024 | 576 | 0.4492 | 0.0067 | 39.3756 | 15.0144 |
| 0.1507 | 2.2194 | 608 | 0.4624 | 0.0067 | 39.8016 | 15.3787 |
| 0.1545 | 2.3364 | 640 | 0.4448 | 0.0067 | 39.1346 | 14.5151 |
| 0.1431 | 2.4534 | 672 | 0.4501 | 0.0067 | 39.7007 | 14.9604 |
| 0.1453 | 2.5704 | 704 | 0.4495 | 0.0067 | 39.3980 | 15.0504 |
| 0.1435 | 2.6874 | 736 | 0.4595 | 0.0067 | 39.9361 | 14.9019 |
| 0.1416 | 2.8044 | 768 | 0.4583 | 0.0067 | 39.9249 | 14.9604 |
| 0.1459 | 2.9214 | 800 | 0.4549 | 0.0067 | 39.9809 | 15.0999 |