Openlrc

Latest version: v1.5.2

Safety actively analyzes 706267 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 4 of 5

0.1.4

This update add input video support and introduce context configuration.

New features:

- Add `word_align` and `sentence_split` for non-word-boundary languages to split long text into sentences.
- Add text-normalization for help matching sentences.
- Add skip-translation support.

Other Changes:

- Use `pathlib` to handle paths.
- Improve timeline accuracy.

0.1.3

This update add input video support and introduce context configuration.

New features:

- Add input video support.
- Add context configuration for inputs.

Other Changes:

- Add test suites to CI.
- Add language detection for translated content.
- Improve prompt by adding background info.
- Update punctuator model.
- Replace `opencc` with more light-weight `zhconv`.

0.1.2

This update improves the timeline consistency of translated subtitles.
Thanks [gpt-subtrans](https://github.com/machinewrapped/gpt-subtrans)!

New features:

- Fix misaligned timeline issue by improving translation prompt.
- Add output srt format support.
- Add changeable temperature and top_p parameter for GPTBot.

Other Changes:

- Report total OpenAI translation fee for multiple audios.
- Improve repeat-checking algorithm.

0.1.1

This update enhances the efficiency of processing multiple audio files.

New features:

- Implementation of a producer-consumer model to process multiple audio files.

Other Changes:

- Update logger with colored format.
- Minor parameter modification that makes the timeline of translation more intuitive.

0.1.0

This update significantly improves translation quality, but at the cost of slower translation speed.

New Features:

- Use multi-step prompt for translation.
- Update the default model to `gpt-3.5-turbo-16k`.
- Automatically fix json encoder error using GPT.

Other Changes:

- Calculate the accurate price for OpenAI API requests.

0.0.6

This update greatly improves the quality of transcription (both in time-alignment and text-quality).

New Features:

- Use `whisperx` to improve transcription accuracy.
- Add Traditional Chinese to Mandarin optimization when `target_lang=zh-cn`.

Page 4 of 5

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.