Downloads · 30 days
5
9% of all-time downloads
oyqiz/wav2vec2-large-xls-r-300m-turkish-colab
wav2vec2-large-xls-r-300m-turkish-colab is a automatic speech recognition model from oyqiz. 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
5
9% of all-time downloads
All-time downloads
54
Public
Repo size
2.5 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 common_voice 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 |
|---|---|---|---|---|
| 4.1319 | 3.67 | 400 | 0.7395 | 0.7031 |
| 0.4204 | 7.34 | 800 | 0.4483 | 0.4687 |
| 0.1895 | 11.01 | 1200 | 0.4355 | 0.4147 |
| 0.1259 | 14.68 | 1600 | 0.4346 | 0.3790 |
| 0.0952 | 18.35 | 2000 | 0.4335 | 0.3448 |
| 0.0754 | 22.02 | 2400 | 0.3980 | 0.3353 |
| 0.0593 | 25.69 | 2800 | 0.3974 | 0.3151 |
| 0.0478 | 29.36 | 3200 | 0.3928 | 0.3065 |