Spaces:
Sleeping
Sleeping
Commit History
-
feat: Switch to minimal Coqui TTS VITS model implementation
Samarth Naik- Replace Piper with Coqui TTS using tts_models/en/ljspeech/vits - Simplify API to basic text-to-speech functionality - Remove complex voice selection and speed controls - Use single high-quality English VITS model - Optimize for minimal dependencies and faster deployment - Add proper .gitignore for audio files and test outputs - Update all documentation for VITS model usage1059c3e -
feat: Switch from Coqui TTS to Piper TTS for better performance
Samarth Naik- Replace heavy Coqui TTS with lightweight Piper TTS - Add support for multiple voice models and quality levels - Implement speed control for speech synthesis - Dramatically reduce Docker image size and build time - Add voice discovery endpoint (/voices) - Automatic model downloading on first use - Update all documentation and test scripts - Optimize for fast CPU-only inference on HF Spacesbe42ab9 -
fix: Optimize dependencies and Dockerfile for HF Spaces build
Samarth Naik- Simplify requirements.txt to avoid dependency conflicts - Use staged Docker builds for better reliability - Install PyTorch CPU version first, then TTS library - Add git dependency for TTS model downloads - Use Python 3.10 for better compatibility9edbda4 -
fix: Update HF Space config to use docker SDK and add Dockerfile
Samarth Naik- Change from fastapi SDK to docker SDK (supported by HF Spaces) - Add Dockerfile for containerized deployment - Install required system dependencies for audio processing34bde63 -
feat: Add production-ready Text-to-Speech API with Coqui TTS
Samarth Naik- Implement FastAPI-based TTS API with xtts_v2 model - Add support for voice cloning with speaker WAV files - Include comprehensive error handling and logging - Add GET and POST endpoints for flexible usage - Configure for CPU-only inference on Hugging Face Spaces - Add test suite and documentation - Update HF Space config from Gradio to FastAPI3135113 -
initial commit
Verified signaturea66eb6f