Skip to main content

Use OpenAI's whisper to generate subtitles in multiple languages for the purpose of language learning

Project description

Language learning application that uses openai's whisper to generate foreign language and English subtitles for videos simultaneously to help with language learning.

Installation

> pip install llsubtitles

Usage

To use llsubtitles first you need a foreign language .mp4 file. I recommend using yt-dlp to download content for language learning. Once you have a .mp4 file you can use llsubtitles to generate subtitles for it.

# Using chinese content for this example
> llsubtitles --language Chinese --model small --combined --definitions --pinyin example.mp4

--language: Refers to the language used by openai's whisper to generate subtitles.
--model: The model used by whisper. See their documentation for more options.
--combined: If this flag is used, the subtitles will be generated in both the foreign language and English.
--definitions: If this flag is used, the subtitles will include definitions for the foreign language words.
--pinyin: Optional flag for Chinese learners, if this flag is used, the subtitles will include pinyin for the Chinese words.

Note, you should make sure that you have pytorch set up correctly to use Cuda if you're using an Nvidia GPU. See pytorch's documentation for more information. This will greatly improve performance.

Credits

Chinese English dictionary is courtesy of cedict

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llsubtitles-1.0.1.tar.gz (3.6 MB view details)

Uploaded Source

Built Distribution

llsubtitles-1.0.1-py3-none-any.whl (3.7 MB view details)

Uploaded Python 3

File details

Details for the file llsubtitles-1.0.1.tar.gz.

File metadata

  • Download URL: llsubtitles-1.0.1.tar.gz
  • Upload date:
  • Size: 3.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.2 CPython/3.8.10 Linux/5.10.16.3-microsoft-standard-WSL2

File hashes

Hashes for llsubtitles-1.0.1.tar.gz
Algorithm Hash digest
SHA256 2a8552f113a6551a4508984d14958897d0cb2813f59f32a94ae765c082b809f8
MD5 c4ecd8ef436faf845e6425d555eb0d9f
BLAKE2b-256 83337c82df327b1b380d000bee1f98ff51939067dca291d1a69be3737d838132

See more details on using hashes here.

File details

Details for the file llsubtitles-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: llsubtitles-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.7 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.3.2 CPython/3.8.10 Linux/5.10.16.3-microsoft-standard-WSL2

File hashes

Hashes for llsubtitles-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 af26f21e0cef99321ca18fe959abfeae5e255e33ada52762c86698b1d2e6f8aa
MD5 83ddfa3a887bf2627282fce648362ab4
BLAKE2b-256 35b2d758a27c0465ebc6e4ffef7d4745bfd5032552ac573bffdcc79d63466f9d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page