requirements.txt

torch
numpy
transformers==4.52.3
accelerate
qwen-omni-utils[decord]
librosa
Pillow
tqdm
scikit-learn

# Optional on compatible NVIDIA GPUs: flash-attn
# Optional NVDEC backend: PyNvVideoCodec
Initial commit: Omni-only turn-taking experiment scaffold. 2026-08-16 00:02:58 +08:00			`torch`
			`numpy`
			`transformers==4.52.3`
			`accelerate`
			`qwen-omni-utils[decord]`
			`librosa`
			`Pillow`
Add reproducible EasyCom causal head pipeline 2026-08-16 22:19:43 +08:00			`tqdm`
			`scikit-learn`
Initial commit: Omni-only turn-taking experiment scaffold. 2026-08-16 00:02:58 +08:00
			`# Optional on compatible NVIDIA GPUs: flash-attn`
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			`# Optional NVDEC backend: PyNvVideoCodec`