Downloads · 30 days
6
22% of all-time downloads
dianavdavidson/wav2vec2-large-xlsr-53-vaani-62031-normalized-alldata-1e-4-epochs-50-FT
wav2vec2-large-xlsr-53-vaani-62031-normalized-alldata-1e-4-epochs-50-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
6
22% of all-time downloads
All-time downloads
27
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 |
|---|---|---|---|---|
| 7.6208 | 1.0 | 540 | 1.2497 | 90.6024 |
| 1.3532 | 2.0 | 1080 | 0.4690 | 39.3999 |
| 0.7834 | 3.0 | 1620 | 0.3268 | 24.3516 |
| 0.5597 | 4.0 | 2160 | 0.2925 | 23.1077 |
| 0.4394 | 5.0 | 2700 | 0.2712 | 19.0855 |
| 0.3611 | 6.0 | 3240 | 0.2690 | 17.8868 |
| 0.3051 | 7.0 | 3780 | 0.2712 | 18.8970 |
| 0.2647 | 8.0 | 4320 | 0.2785 | 17.7322 |
| 0.2267 | 9.0 | 4860 | 0.2804 | 17.1705 |
| 0.2043 | 10.0 | 5400 | 0.2973 | 15.5986 |
| 0.1841 | 11.0 | 5940 | 0.2919 | 15.5873 |
| 0.1657 | 12.0 | 6480 | 0.3025 | 15.2518 |
| 0.1403 | 13.0 | 7020 | 0.3089 | 14.9578 |
| 0.1309 | 14.0 | 7560 | 0.3196 | 14.3999 |
| 0.1250 | 15.0 | 8100 | 0.3204 | 13.9551 |
| 0.1149 | 16.0 | 8640 | 0.3112 | 14.2604 |
| 0.1113 | 17.0 | 9180 | 0.3230 | 14.4602 |
| 0.1060 | 18.0 | 9720 | 0.3363 | 13.4009 |
| 0.0979 | 19.0 | 10260 | 0.3237 | 14.0644 |
| 0.0974 | 20.0 | 10800 | 0.3402 | 13.5970 |
| 0.0951 | 21.0 | 11340 | 0.3361 | 14.1021 |