High-Quality Voice Cloning TTS for 600+ Languages
Python
Commits on master
switch to torchaudio resampling for consistency with training
6a3f23d Han Zhu committed 7 months ago
use soundfile+librosa instead of torchaudio to avoid issues on some devices
4f4b0cc Han Zhu committed 7 months ago
fix: batch_inference without ref_text or ref_audio_path (#70)
88596a0 Pol Pastells committed 7 months ago