Add StyleTTS2 integration scripts for voice cloning and lip sync pipeline 66e2a44 marcos commited on Dec 11, 2025
fix: convert all audio to WAV 16kHz PCM before processing (#379) a18f536 unverified Alexey commited on Sep 26, 2025
fix: ensure upper bond does not go below zero in landmark extraction (#329) fa6abed unverified ykani commited on Jul 2, 2025
fix: use torch.no_grad() in inference to prevent excessive memory usage (~30GB) with inference (#349) 5214b81 unverified gaolegao commited on Jul 2, 2025
feat: windows infer & gradio (#312) 2967472 unverified Zhizhou Zhong zzgoogle commited on Apr 12, 2025
feat: data preprocessing and training (#294) 84ee34a unverified Zhizhou Zhong commited on Apr 4, 2025
<enhance>(inference): support using an image as video input(#17 #34) 6322edc czk32611 commited on Apr 19, 2024
Fix fps calculation bug in realtime_inference.py (#35) 6f026d1 unverified itechmusic commited on Apr 18, 2024