Web app to transform audio into text from multiple audio formats and languages using Google's Speech-to-Text while respecting the limits of its free API level.
Note: This project was developed for study purposes only and should not be used in production.
-
Make sure you have Docker and Docker Compose installed on your machine.
-
Clone this repository to your machine using the command:
git clone git@github.com:dahn94/GlobalSpeechToText.git
- Access the project directory with the command:
cd GlobalSpeechToText
- Run the command to bring up the container:
docker-compose -f docker-compose.yml up --build
Describe a use of this fastapi project with url, method, request body, response body, etc. This projects accepts audio files in mp3, m4a and wav format.
The project dependencies are listed in the pyproject.toml file.
This project is open to contributions and improvements. Any suggestion or correction is welcome.
This project is licensed under the MIT license. See the LICENSE file for more information.