No Description

Lengyue 7704bb7d09 Fix filename 2 years ago
preparing_data a003e5a390 Add utilities & whisper vq model 2 years ago
speech_lm 7704bb7d09 Fix filename 2 years ago
.dockerignore 70797ef7d5 Add dockerignore 2 years ago
.gitignore a003e5a390 Add utilities & whisper vq model 2 years ago
.pre-commit-config.yaml e4ce816175 Update deps 2 years ago
README.md 3fc0a688ca Update Readme 2 years ago
dockerfile 9920873cf2 Optimize schedule 2 years ago
requirements.txt a003e5a390 Add utilities & whisper vq model 2 years ago
setup.py 7650b2ac43 Update much robust dataloader 2 years ago

README.md

Speech LLM

Setup

# Basic environment setup
conda create -n speech-llm python=3.10
conda activate speech-llm
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia

# Install requirements
pip3 install -r requirements.txt

# Install flash-attn
MAX_JOBS=4 pip install flash-attn --no-build-isolation

# Install speech-llm
pip3 install -e .