Downloads · 30 days
4
1% of all-time downloads
ai-project/wav2vec2-large-xls-r-300m-vi-25p
wav2vec2-large-xls-r-300m-vi-25p is a automatic speech recognition model from ai-project. 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
4
1% of all-time downloads
All-time downloads
285
Public
Repo size
6.3 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 |
|---|---|---|---|---|
| 7.448 | 2.4 | 400 | inf | 1.0 |
| 2.8589 | 4.79 | 800 | inf | 0.7777 |
| 1.4919 | 7.19 | 1200 | inf | 0.5968 |
| 1.1255 | 9.58 | 1600 | inf | 0.5540 |
| 0.9354 | 11.98 | 2000 | inf | 0.4970 |
| 0.7816 | 14.37 | 2400 | inf | 0.4799 |
| 0.6822 | 16.77 | 2800 | inf | 0.4785 |
| 0.5768 | 19.16 | 3200 | inf | 0.4704 |
| 0.5031 | 21.56 | 3600 | inf | 0.4609 |
| 0.4589 | 23.95 | 4000 | inf | 0.4585 |
| 0.4136 | 26.35 | 4400 | inf | 0.4592 |
| 0.3829 | 28.74 | 4800 | inf | 0.4537 |