williambrunos / whisper-AI-audio-transcriber

This repository is intended to store the artifacts needed to transcribe an audio file using whisper AI model

Whisper AI transcriber

This project has the objective to ilustrate how to perform an audio transcription using the Whisper AI model from OpenAI.

Further read: Introducing Whisper AI

How to set up the project locally

1. Clone the project:

git clone https://github.com/williambrunos/whisper-AI-audio-transcriber.git

2. Open the project locally
3. Rename the .env.example file to .env
4. Fill the value of the property OPENAI_API_KEY in the .env file with your own openai key

You can see how to set up an openai key in this tutorial:

OpenAI Quickstart

5. Set up a python venv

python -m venv venv

6. Activate the venv with one of the following commands

For windows cmd

venv\Scripts\activate

For windows powershell

venv\Scripts\Activate.ps1

For linux and mac os

venv\Scripts\activate.bat

7. Install the dependencies in the venv

pip install -r requirements.txt

8. Run the project

python main.py

References

OpenAI Speech to Text