Downloads · 30 days
8
29% of all-time downloads
dianavdavidson/wav2vec2-xls-r-300m-mucs-62255-hinglish_mixed_scripts-25_45-1e-4-epochs-100-FT
wav2vec2-xls-r-300m-mucs-62255-hinglish_mixed_scripts-25_45-1e-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
8
29% of all-time downloads
All-time downloads
28
Public
Parameters
316M
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-xls-r-300m 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 |
|---|---|---|---|---|
| No log | 1.0 | 440 | 3.6685 | 100.0 |
| 15.2113 | 2.0 | 880 | 1.2668 | 53.7757 |
| 3.8030 | 3.0 | 1320 | 0.9658 | 33.7910 |
| 1.4463 | 4.0 | 1760 | 0.8572 | 30.2059 |
| 1.1025 | 5.0 | 2200 | 0.8759 | 29.9226 |
| 0.8903 | 6.0 | 2640 | 0.8302 | 27.9176 |
| 0.7503 | 7.0 | 3080 | 0.7923 | 28.0266 |
| 0.6503 | 8.0 | 3520 | 0.7942 | 25.3896 |
| 0.6503 | 9.0 | 3960 | 0.7970 | 25.9780 |
| 0.5636 | 10.0 | 4400 | 0.8209 | 27.4273 |
| 0.4978 | 11.0 | 4840 | 0.8060 | 24.8883 |
| 0.4468 | 12.0 | 5280 | 0.8197 | 24.7684 |
| 0.4007 | 13.0 | 5720 | 0.8391 | 24.8338 |
| 0.3383 | 14.0 | 6160 | 0.8844 | 23.5916 |
| 0.3124 | 15.0 | 6600 | 0.8811 | 24.1909 |
| 0.2690 | 16.0 | 7040 | 0.9029 | 23.5371 |
| 0.2690 | 17.0 | 7480 | 0.8648 | 23.8422 |
| 0.2327 | 18.0 | 7920 | 0.9188 | 24.3980 |
| 0.2024 | 19.0 | 8360 | 0.9195 | 22.8070 |
| 0.1824 | 20.0 | 8800 | 0.9267 | 22.7525 |
| 0.1726 | 21.0 | 9240 | 0.8933 | 22.3058 |
| 0.1521 | 22.0 | 9680 | 0.9683 | 22.7089 |
| 0.1434 | 23.0 | 10120 | 0.9119 | 22.0333 |
| 0.1305 | 24.0 | 10560 | 0.9927 | 21.6302 |
| 0.1224 | 25.0 | 11000 | 1.0215 | 21.8481 |
| 0.1224 | 26.0 | 11440 | 1.0045 | 21.9026 |
| 0.1123 | 27.0 | 11880 | 1.0483 | 22.2295 |