https://github.com/escarrie/transcriptaudio

This is a script that can be used to transcript audio file into text file using Whisper AI
https://github.com/escarrie/transcriptaudio

ai transcription whisper

Last synced: 6 days ago
JSON representation

This is a script that can be used to transcript audio file into text file using Whisper AI

• Host: GitHub
• URL: https://github.com/escarrie/transcriptaudio
• Owner: escarrie
• Created: 2024-11-12T11:01:21.000Z (2 months ago)
• Default Branch: master
• Last Pushed: 2024-11-16T16:29:04.000Z (2 months ago)
• Last Synced: 2024-11-16T17:18:37.476Z (2 months ago)
• Topics: ai, transcription, whisper
• Language: Python
• Homepage:
• Size: 1.95 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Description

This project allows you to obtain a transcription of an audio file.

The audio file must be in either .wav or .m4a format.

# Installation

1. Ensure you have Python 3 installed on your system. You can download it from [python.org](https://www.python.org/).

2. Install Python virtual environment:

    ```sh

    python3 -m venv env

    ```

3. Activate the virtual environment:

    - On Windows:

        ```sh

        .\env\Scripts\activate

        ```

    - On macOS and Linux:

        ```sh

        source env/bin/activate

        ```

4. Install the required dependencies:

    ```sh

    pip install -r requirements.txt

    ```

You are now ready to use the transcription project.

# Usage

To use this project, place each of your audio files (.wav, .m4a) in the `files` folder. Then, run the script:

```sh

python app.py

```

Once the transcription is complete, the transcriptions will be available in .txt format in the same folder.