Downloads · 30 days
3
1% of all-time downloads
4m1g0/wav2vec2-large-xls-r-53m-gl-jupyter2
wav2vec2-large-xls-r-53m-gl-jupyter2 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
312
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-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 |
|---|---|---|---|---|
| 3.7298 | 3.36 | 400 | 0.2477 | 0.2493 |
| 0.1507 | 6.72 | 800 | 0.1294 | 0.1264 |
| 0.066 | 10.08 | 1200 | 0.1235 | 0.1161 |
| 0.0456 | 13.44 | 1600 | 0.1011 | 0.1001 |
| 0.0347 | 16.8 | 2000 | 0.1033 | 0.0909 |
| 0.0284 | 20.17 | 2400 | 0.1083 | 0.0861 |
| 0.0221 | 23.53 | 2800 | 0.1010 | 0.0761 |
| 0.0199 | 26.89 | 3200 | 0.0911 | 0.0754 |
| 0.0155 | 30.25 | 3600 | 0.1026 | 0.0743 |
| 0.0142 | 33.61 | 4000 | 0.1024 | 0.0719 |
| 0.0125 | 36.97 | 4400 | 0.0977 | 0.0676 |
| 0.0104 | 40.33 | 4800 | 0.0945 | 0.0664 |
| 0.0089 | 43.69 | 5200 | 0.0941 | 0.0615 |