Downloads · 30 days
9
3% of all-time downloads
avtanh/wav2vec2-large-xls-r-300m-vietnamese-colab
wav2vec2-large-xls-r-300m-vietnamese-colab is a automatic speech recognition model from avtanh. 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
9
3% of all-time downloads
All-time downloads
271
Public
Repo size
13.9 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 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 |
|---|---|---|---|---|
| 7.9109 | 12.49 | 400 | 2.3779 | 0.9890 |
| 0.7906 | 24.98 | 800 | 1.3130 | 0.7196 |