If you are looking to generate audio and music from text using AI locally on your laptop or in AWS instance, then this is the step by step guide with all the commands.
Specs:
AWS Instance = c5.xlarge
OS: Ubuntu 22.04.2 LTS
Commands Used:
1 apt-get update
2 curl -v google.com
3 conda --version
ffmpeg -version
4 apt-get install wget
5 cd /tmp
6 wget https://repo.anaconda.com/archive/Anaconda3-2022.05-Linux-x86_64.sh
7 sha256sum Anaconda3-2022.05-Linux-x86_64.sh
8 bash Anaconda3-2022.05-Linux-x86_64.sh
9 source ~/.bashrc
10 conda info
11 conda create -n audiocraft python=3.9
12 conda activate audiocraft
13 apt install ffmpeg
14 ffmpeg -version
15 git clone https://github.com/facebookresearch/audiocraft.git
16 cd audiocraft/
17 python -m pip install -r requirements.txt
18 python -m demos.musicgen_app --share
19 history
22 conda env list
24 conda deactivate
25 conda remove -n audiocraft --all
26 conda env list
27 history
No comments:
Post a Comment