requirements.txt

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

# Used by train_omni_turn_lora.py; already included in the ms-swift image.
peft

# Optional on compatible NVIDIA GPUs: flash-attn
# Optional CPU video backend: torchcodec
# 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
Add cached AV pipeline for Omni turn LoRA 2026-08-23 14:40:03 +08:00			`# Used by train_omni_turn_lora.py; already included in the ms-swift image.`
			`peft`

Initial commit: Omni-only turn-taking experiment scaffold. 2026-08-16 00:02:58 +08:00			`# Optional on compatible NVIDIA GPUs: flash-attn`
Add TorchCodec video backend 2026-08-23 16:41:05 +08:00			`# Optional CPU video backend: torchcodec`
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`