https://github.com/m1guelpf/yt-whisper

Using OpenAI's Whisper to automatically generate YouTube subtitles
https://github.com/m1guelpf/yt-whisper

ffmpeg openai openai-whisper subtitles subtitles-generated transcribe whisper youtube youtube-dl

Last synced: 1 day ago
JSON representation

Using OpenAI's Whisper to automatically generate YouTube subtitles

• Host: GitHub
• URL: https://github.com/m1guelpf/yt-whisper
• Owner: m1guelpf
• License: mit
• Created: 2022-09-22T16:29:29.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-01-16T09:18:11.000Z (10 months ago)
• Last Synced: 2024-10-29T17:28:14.862Z (10 days ago)
• Topics: ffmpeg, openai, openai-whisper, subtitles, subtitles-generated, transcribe, whisper, youtube, youtube-dl
• Language: Python
• Homepage:
• Size: 15.6 KB
• Stars: 1,360
• Watchers: 18
• Forks: 139
• Open Issues: 24
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-whisper - yt-whisper - YouTube subtitle generation. (CLI tools / Self-hosted)
• awesome-openai-whisper - Automatic YouTube subtitle generation
• StarryDivineSky - m1guelpf/yt-whisper

README

        
# Automatic YouTube subtitle generation

This repository uses `yt-dlp` and [OpenAI's Whisper](https://openai.com/blog/whisper) to generate subtitle files for any youtube video.

## Installation

To get started, you'll need Python 3.7 or newer. Install the binary by running the following command:

    pip install git+https://github.com/m1guelpf/yt-whisper.git

You'll also need to install [`ffmpeg`](https://ffmpeg.org/), which is available from most package managers:

```bash

# on Ubuntu or Debian

sudo apt update && sudo apt install ffmpeg

# on MacOS using Homebrew (https://brew.sh/)

brew install ffmpeg

# on Windows using Chocolatey (https://chocolatey.org/)

choco install ffmpeg

```

## Usage

The following command will generate a VTT file from the specified YouTube video

    yt_whisper "https://www.youtube.com/watch?v=dQw4w9WgXcQ"

The default setting (which selects the `small` model) works well for transcribing English. You can optionally use a bigger model for better results (especially with other languages). The available models are `tiny`, `tiny.en`, `base`, `base.en`, `small`, `small.en`, `medium`, `medium.en`, `large`.

    yt_whisper "https://www.youtube.com/watch?v=dQw4w9WgXcQ" --model medium

Adding `--task translate` will translate the subtitles into English:

    yt_whisper "https://www.youtube.com/watch?v=dQw4w9WgXcQ" --task translate

Run the following to view all available options:

    yt_whisper --help

## License

This script is open-source and licensed under the MIT License. For more details, check the [LICENSE](LICENSE) file.