README.md

Audiogrammer

A Python app for making custom audiograms with built-in captioning engine

Example Output

Barry.Cant.Swim.1.mp4

UI

Setup

Follow these instructions to run locally. Either install locally or if you have docker installed using the docker commands.

Install Locally

1. Make sure ffmpeg and imagemagic are installed

//Linux
sudo apt install ffmpeg imagemagick

//Mac
brew install ffmpeg imagemagick

2. Install pip packages

pip install -r requirements.txt

3. Install speech-to-text model

wget https://alphacephei.com/vosk/models/vosk-model-en-us-0.42-gigaspeech.zip -O model/model_files.zip && unzip model/model_files.zip -d model && mv model/vosk-model-en-us-0.42-gigaspeech/* model/ && rm -r model/vosk-model-en-us-0.42-gigaspeech

3. Run the server

python app.py

Install with Docker

If you install this way make sure it is a clean copy of the folder structure (model and uploads should be empty to avoid issues)

1. Get base image

docker pull python:3.9-buster

2. Build

docker-compose build

3. Run

docker-compose up