audio-flamingo-3 / requirements.txt
SreyanG-NVIDIA's picture
Upload 225 files
174ae06 verified
raw
history blame
987 Bytes
# Core Python version used in the environment
python==3.10.14
# Core dependencies from pyproject.toml
torch==2.3.0
torchvision==0.18.0
transformers==4.46.0
tokenizers>=0.15.2
sentencepiece==0.1.99
shortuuid
accelerate==0.34.2
peft>=0.9.0
bitsandbytes==0.43.2
pydantic>=1,<2
markdown2[all]
numpy==1.26.4
scikit-learn==1.2.2
gradio==3.35.2
gradio_client==0.2.9
requests
httpx
uvicorn
fastapi
fire
seaborn
ring_flash_attn==0.1.1
einops==0.6.1
einops-exts==0.0.4
timm==0.9.12
openpyxl==3.1.2
pytorchvideo==0.1.5
decord==0.6.0
datasets==2.16.1
openai==1.8.0
webdataset==0.2.86
nltk==3.3
pywsd==1.2.4
opencv-python-headless==4.8.0.76
tyro
pytest
pre-commit
loguru
hydra-core
xgrammar
# Direct Git dependency
git+https://github.com/bfshi/scaling_on_scales#egg=s2wrapper
# Additional dependencies from shell script
flash-attn==2.7.3
torchaudio==2.3
soundfile
librosa
openai-whisper
ftfy
ffmpeg
jiwer
kaldiio
protobuf==3.20.*
triton==3.1.0 # Override to latest only if using FP8 quantization