Dataset used for training:
- Name: Common Voice
- Language: Indonesian [id]
- Version: 6.1
Test WER: 19.3 %
Repo for training:
https://github.com/bagustris/wav2vec2-indonesian
NEWEST VERSION AVAILABLE HERE WITH SMALLER MODEL AND SMALLER WER (5.9%):
https://huggingface.co/Bagus/whisper-small-id-cv17
Contact:
bagus@ep.its.ac.id
- Downloads last month
- 27,317
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.