FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV PIP_NO_CACHE_DIR=1
RUN apt-get update && apt-get install -y \
python3 python3-pip python3-dev \
git wget curl vim tmux \
build-essential cmake ninja-build \
libsndfile1 libsndfile1-dev ffmpeg \
&& rm -rf /var/lib/apt/lists/*
RUN python3 -m pip install --upgrade pip setuptools wheel
RUN pip3 install \
torch==2.1.2 \
torchvision==0.16.2 \
torchaudio==2.1.2 \
--index-url https://download.pytorch.org/whl/cu121
RUN pip3 install \
pytorch-lightning==1.6.5.post0 \
soundfile==0.13.1 \
torch-ema==0.3 \
torch-pesq==0.1.2 \
torchelastic==0.2.2 \
torchmetrics==0.9.3 \
torchtyping==0.1.5 \
wandb==0.13.10
WORKDIR /workspace
CMD ["/bin/bash"]
FlowSE 를 위한 도커파일임
S. Lee, S. Cheong, S. Han, and J. W. Shin,
“FlowSE: Flow Matching-based Speech Enhancement,”
in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
Hyderabad, India, 2025, pp. 1-5,
doi: 10.1109/ICASSP49660.2025.10888274.
@INPROCEEDINGS{10888274,
author={Lee, Seonggyu and Cheong, Sein and Han, Sangwook and Shin, Jong Won},
booktitle={ICASSP 2025 – 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
title={FlowSE: Flow Matching-based Speech Enhancement},
year={2025},
doi={10.1109/ICASSP49660.2025.10888274}
}