High-Quality Voice Cloning TTS for 600+ Languages
Python
Commits on master
Fix: type of input waveform in process method in `denoise_audio.py` (#254)
08be0b4 润心 committed 2 months ago
feat: add optional LoRA finetuning support via PEFT (#243)
38e992b Kawshik Kumar Paul committed 3 months ago
feat: FlashInfer-accelerated inference (2-2.9x lossless speedup) (#239)
28bc088 Yuekai Zhang committed 3 months ago
docs: add LocalText2Voice to community projects (#230)
468e927 Esteban García committed 4 months ago
Add opt-in text normalization (numbers, dates, currency) via generate(normalize_text=True) (#227)
52aa404 Chao Cao committed 4 months ago
Avoid decoding the full reference audio just to get its duration (#220)
7ff52a1 aradix85 committed 4 months ago
Add VoiceClonePrompt.save()/load() for cross-session voice reuse (#223)
db1039f Chao Cao committed 4 months ago
Honor asr_model_name when the ASR model is loaded lazily (#221)
1574e06 Chao Cao committed 4 months ago
Fix flex_attention silently running fp32 under bf16 mixed precision (#212)
d3a9e35 Shi Shuai committed 4 months ago
Add CI workflows (PyPI publish, pre-commit) and format codebase with ruff
9c3ab46 Han Zhu committed 4 months ago
Expose pad_duration and fade_duration to let users control fade-in/out and silence padding
398b611 Han Zhu committed 4 months ago
Fix END_PUNCTUATION dropping members due to unescaped triple quote (#181) (#182)
9948396 Dongryul Min committed 5 months ago