wav2vec2-indonesian-javanese-sundanese
indonesian-nlp/wav2vec2-indonesian-javanese-sundanese
A popular open speech-to-text model, with 4.1M downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.
about this model
indonesian-nlp/wav2vec2-indonesian-javanese-sundanese is an automatic speech recognition (ASR) model that transcribes speech in Indonesian, Javanese, and Sundanese. It is fine-tuned from facebook/wav2vec2-large-xlsr-53 on the Indonesian Common Voice dataset, High-quality TTS data for Javanese (SLR41), and High-quality TTS data for Sundanese (SLR44).
Key Strengths
- Multilingual: supports three major languages of Indonesia without requiring language identification.
- Direct transcription without a separate language model.
- Input speech must be sampled at 16 kHz.
Benchmark Results
Evaluated on the Indonesian Common Voice test set, the model achieves a Word Error Rate (WER) of 11.57%.
Live Demo
A live demo is available to test the model interactively.
This model is hosted by Gigarouter as a managed, OpenAI-compatible API. Users send audio and receive transcribed text without managing infrastructure.
We're benchmarking and onboarding wav2vec2-indonesian-javanese-sundanese as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.