Downloads · 30 days
2
6% of all-time downloads
mfaiq2307/faiq-wav2vec2-large-xlsr-indo-demo-t4-batch32
faiq-wav2vec2-large-xlsr-indo-demo-t4-batch32 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
2
6% of all-time downloads
All-time downloads
33
Public
Repo size
8.8 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-large-xlsr-53 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 |
|---|---|---|---|---|
| 4.4776 | 5.84 | 400 | 2.6299 | 1.0001 |
| 0.7344 | 11.68 | 800 | 0.3744 | 0.5020 |
| 0.248 | 17.52 | 1200 | 0.3572 | 0.4595 |
| 0.1687 | 23.36 | 1600 | 0.3576 | 0.4300 |
| 0.1386 | 29.2 | 2000 | 0.3666 | 0.4217 |