AudioNotes

Audio and video to structured note-taking system based on FunASR and Qwen2

It can quickly extract the content of audio and video, and call a large model to organize it into a structured markdown note for easy and quick reading.

FunASR: https://github.com/modelscope/FunASR

Qwen2: https://ollama.com/library/qwen2

Effect display

Audio and video recognition and sorting

Talk to audio and video content

How to use

① Install Ollama

Download the Ollama installation package corresponding to the system and install it.

https://ollama.com/download

② Pull model

I take阿里的千问2 7b as an example https://ollama.com/library/qwen2

ollama pull qwen2:7b

③ Deployment services

There are two deployment methods, one is to deploy using Docker and the other is to deploy locally.

Docker deployment (recommended)?

curl -fsSL https://github.com/harry0703/AudioNotes/raw/main/docker-compose.yml -o docker-compose.yml
docker-compose up

After docker starts, visit http://localhost:15433/

The login account is admin and the password is admin (can be modified in the docker-compose.yml file)

Local deployment?

An accessible postgresql database is required

conda create -n AudioNotes python=3.10 -y
conda activate AudioNotes
git clone https://github.com/harry0703/AudioNotes.git
cd AudioNotes
pip install -r requirements.txt

Rename .env.example to .env and modify related configuration information