Downloads · 30 days
14
2% of all-time downloads
lgris/wav2vec2-xls-r-1b-portuguese-CORAA-3
wav2vec2-xls-r-1b-portuguese-CORAA-3 is a automatic speech recognition model from lgris. 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
14
2% of all-time downloads
All-time downloads
642
Public
Repo size
11.6 GB
Likes
0
Public
Click a slice to open those files.
.bin3.9 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on CORAA 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 |
|---|---|---|---|---|
| 2.0169 | 0.21 | 5000 | 1.9582 | 0.9283 |
| 1.8561 | 0.42 | 10000 | 1.6144 | 0.8554 |
| 1.6823 | 0.63 | 15000 | 1.4165 | 0.7710 |
| 1.52 | 0.84 | 20000 | 1.2441 | 0.7289 |
| 1.3757 | 1.05 | 25000 | 1.1061 | 0.6491 |
| 1.2377 | 1.26 | 30000 | 1.0029 | 0.6020 |