agent87/RW-DEEPSPEECH-API
An end to end deep speech REST API containing speech to text and text speech services for Kinyarwanda.
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.
Stars
12
Forks
6
Language
Jupyter Notebook
License
GPL-3.0
Category
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.
Higher-rated alternatives
herimor/voxtream
VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking rate Control
EveryVoiceTTS/EveryVoice
The EveryVoice TTS Toolkit - Text To Speech for your language
kadirnar/VoiceHub
VoiceHub: A Unified Inference Interface for TTS Models
NeonGeckoCom/neon-tts-plugin-coqui
Coqui AI TTS plugin
Atm4x/tts-with-rvc
TTS with RVC-module to generate .wav audios