Downloads · 30 days
3
1% of all-time downloads
4m1g0/wav2vec2-large-xls-r-53m-gl-jupyter5
wav2vec2-large-xls-r-53m-gl-jupyter5 is a automatic speech recognition model from 4m1g0. 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
1% of all-time downloads
All-time downloads
286
Public
Repo size
24 GB
Likes
0
Public
Click a slice to open those files.
.bin1.3 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None 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 |
|---|---|---|---|---|
| 3.6862 | 3.36 | 400 | 0.2455 | 0.2344 |
| 0.1517 | 6.72 | 800 | 0.1195 | 0.1233 |
| 0.0772 | 10.08 | 1200 | 0.1219 | 0.1155 |
| 0.0472 | 13.44 | 1600 | 0.1162 | 0.1034 |
| 0.0357 | 16.8 | 2000 | 0.1070 | 0.1006 |
| 0.0307 | 20.17 | 2400 | 0.1131 | 0.1013 |
| 0.0258 | 23.53 | 2800 | 0.1163 | 0.0847 |
| 0.0229 | 26.89 | 3200 | 0.1100 | 0.0858 |
| 0.0183 | 30.25 | 3600 | 0.1062 | 0.0810 |
| 0.0182 | 33.61 | 4000 | 0.1068 | 0.0800 |
| 0.0151 | 36.97 | 4400 | 0.1088 | 0.0780 |
| 0.0138 | 40.33 | 4800 | 0.1062 | 0.0737 |
| 0.0121 | 43.69 | 5200 | 0.1061 | 0.0722 |
| 0.0088 | 47.06 | 5600 | 0.1055 | 0.0670 |
| 0.008 | 50.42 | 6000 | 0.1059 | 0.0646 |
| 0.007 | 53.78 | 6400 | 0.1020 | 0.0634 |
| 0.0065 | 57.14 | 6800 | 0.1025 | 0.0625 |