agent87/RW-DEEPSPEECH-API

An end to end deep speech REST API containing speech to text and text speech services for Kinyarwanda.

40
/ 100
Emerging

Leverages pre-trained models from Nvidia (Conformer CTC for STT trained on 2000 hours of Kinyarwanda speech) and Digital Umuganda (YourTTS for TTS with zero-shot voice adaptation), exposing both through FastAPI with WebSocket support and Uvicorn. Integrates MongoDB for inference logging, includes Docker containerization for deployment, and uses the Transformers and NeMo libraries for model inference with customization capabilities for domain-specific fine-tuning.

No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 16 / 25

How are scores calculated?

Stars

12

Forks

6

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Feb 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/agent87/RW-DEEPSPEECH-API"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.