Downloads · 30 days
3
8% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-vaani-62079-normalized-alldata-1e-4-epochs-100-FT
wav2vec2-large-xlsr-53-vaani-62079-normalized-alldata-1e-4-epochs-100-FT is a automatic speech recognition model from dianavdavidson. 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
3
8% of all-time downloads
All-time downloads
36
Public
Parameters
315M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 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 | Global Wer |
|---|---|---|---|---|
| 7.6147 | 1.0 | 540 | 1.5298 | 96.0796 |
| 1.3625 | 2.0 | 1080 | 0.5219 | 47.7986 |
| 0.8026 | 3.0 | 1620 | 0.3418 | 26.7039 |
| 0.5712 | 4.0 | 2160 | 0.3021 | 24.0463 |
| 0.4480 | 5.0 | 2700 | 0.2797 | 20.3370 |
| 0.3664 | 6.0 | 3240 | 0.2727 | 18.4296 |
| 0.3050 | 7.0 | 3780 | 0.2805 | 18.5087 |
| 0.2661 | 8.0 | 4320 | 0.2951 | 17.0009 |
| 0.2250 | 9.0 | 4860 | 0.2981 | 18.0451 |
| 0.2042 | 10.0 | 5400 | 0.2983 | 15.3687 |
| 0.1807 | 11.0 | 5940 | 0.3128 | 16.4581 |
| 0.1634 | 12.0 | 6480 | 0.3034 | 14.6223 |
| 0.1403 | 13.0 | 7020 | 0.3210 | 15.1726 |
| 0.1312 | 14.0 | 7560 | 0.3258 | 14.0154 |
| 0.1217 | 15.0 | 8100 | 0.3328 | 14.1699 |
| 0.1145 | 16.0 | 8640 | 0.3373 | 14.2453 |
| 0.1073 | 17.0 | 9180 | 0.3380 | 14.0757 |