19 lines
474 B
Plaintext
19 lines
474 B
Plaintext
torch
|
|
numpy
|
|
# Default for Thinker replay. The B1 local extractor also supports 4.57.6;
|
|
# keep that version in existing GPU containers (see docs/local_feature_baseline.md).
|
|
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
|