Downloads · 30 days
4
10% of all-time downloads
mfaiq2307/faiq-wav2vec2-large-xlsr-indo-demo-colab
faiq-wav2vec2-large-xlsr-indo-demo-colab 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
4
10% of all-time downloads
All-time downloads
42
Public
Repo size
54.3 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-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 |
|---|---|---|---|---|
| 5.0752 | 2.92 | 400 | 2.7911 | 1.0 |
| 1.2625 | 5.84 | 800 | 0.4611 | 0.6152 |
| 0.3806 | 8.76 | 1200 | 0.4284 | 0.5476 |
| 0.2653 | 11.68 | 1600 | 0.4074 | 0.4935 |
| 0.2134 | 14.6 | 2000 | 0.3846 | 0.4788 |
| 0.1701 | 17.52 | 2400 | 0.4175 | 0.4640 |
| 0.1544 | 20.44 | 2800 | 0.4101 | 0.4471 |
| 0.1303 | 23.36 | 3200 | 0.4147 | 0.4457 |
| 0.1202 | 26.28 | 3600 | 0.4050 | 0.4344 |
| 0.1082 | 29.2 | 4000 | 0.4079 | 0.4313 |