PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

Vector Quantized PPGs based Voice conversion

HMAC File Server ensures secure uploads/downloads with HMAC auth, rate limiting, CORS, retries, file versioning, Unix sockets, and Redis. It offers Prometheus metrics and graceful shutdown for efficient, reliable file handling.

Improving the Appropriateness in Cross-Text Prosody Transfer using Human Supervision