Downloads · 30 days
8
21% of all-time downloads
mfaiq2307/faiq-wav2vec2-xls-r-300m-indo-demo-t4
faiq-wav2vec2-xls-r-300m-indo-demo-t4 is a automatic speech recognition model from mfaiq2307. 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
8
21% of all-time downloads
All-time downloads
39
Public
Repo size
15.1 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_11_0 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 |
|---|---|---|---|---|
| 4.815 | 2.92 | 400 | 2.8071 | 1.0 |
| 1.6746 | 5.84 | 800 | 0.5497 | 0.7194 |
| 0.4438 | 8.76 | 1200 | 0.4727 | 0.5856 |
| 0.2924 | 11.68 | 1600 | 0.4389 | 0.5219 |
| 0.2272 | 14.6 | 2000 | 0.4270 | 0.4979 |
| 0.1785 | 17.52 | 2400 | 0.4320 | 0.4868 |
| 0.1589 | 20.44 | 2800 | 0.4483 | 0.4667 |
| 0.1319 | 23.36 | 3200 | 0.4388 | 0.4601 |
| 0.1188 | 26.28 | 3600 | 0.4424 | 0.4456 |
| 0.1061 | 29.2 | 4000 | 0.4348 | 0.4426 |