Downloads · 30 days
2
2% of all-time downloads
4m1g0/wav2vec2-large-xls-r-300m-gl-jupyter4
wav2vec2-large-xls-r-300m-gl-jupyter4 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
2
2% of all-time downloads
All-time downloads
81
Public
Repo size
18.9 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-xls-r-300m 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 |
|---|---|---|---|---|
| 3.492 | 3.36 | 400 | 0.3109 | 0.3158 |
| 0.194 | 6.72 | 800 | 0.1279 | 0.1454 |
| 0.0794 | 10.08 | 1200 | 0.1210 | 0.1240 |
| 0.0565 | 13.44 | 1600 | 0.1209 | 0.1150 |
| 0.041 | 16.8 | 2000 | 0.1186 | 0.1107 |
| 0.0343 | 20.17 | 2400 | 0.1143 | 0.0933 |
| 0.0283 | 23.53 | 2800 | 0.1067 | 0.0900 |
| 0.0231 | 26.89 | 3200 | 0.1076 | 0.0812 |
| 0.0176 | 30.25 | 3600 | 0.1094 | 0.0780 |
| 0.0169 | 33.61 | 4000 | 0.1041 | 0.0766 |
| 0.0138 | 36.97 | 4400 | 0.1012 | 0.0711 |
| 0.0109 | 40.33 | 4800 | 0.0985 | 0.0655 |
| 0.0099 | 43.69 | 5200 | 0.0970 | 0.0636 |