7 Commits

Author	SHA1	Message	Date
Xin Wang	d426b4740a	Add causal person fusion and MuVAP stage-3 baselines	2026-09-10 06:54:22 +08:00
Xin Wang	c4feeb47f4	Fix transformers version	2026-08-27 15:24:59 +08:00
Xin Wang	c844673984	Add TorchCodec video backend	2026-08-23 16:41:05 +08:00
Xin Wang	1069a0beee	Add cached AV pipeline for Omni turn LoRA	2026-08-23 14:40:03 +08:00
Xin Wang	24cb92f1f4	Add support for NVDEC backend in video processing and enhance README documentation. Introduce a new script for extracting EasyCom sessions on specific GPUs, detailing session management and error handling. Update requirements.txt to include PyNvVideoCodec as an optional dependency. Refactor streaming_turn_model_directly.py to accommodate multiple decoder backends and improve frame indexing with ffprobe.	2026-08-18 08:41:54 +08:00
Xin Wang	080c45f049	Add reproducible EasyCom causal head pipeline	2026-08-16 22:19:43 +08:00
Xin Wang	bde72487bb	Initial commit: Omni-only turn-taking experiment scaffold. ... Add EasyCom prep, Qwen2.5-Omni feature extraction, streaming turn model prototype, and docs for the ICASSP 2027 ego-speak study. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-08-16 00:02:58 +08:00