v1.0.1

This update fixes minor issues.

Other Changes:

• Fix an issue that prevents the usage of whisper-large-v3.
• Remove tags from translation texts.

v1.0.0

0.1.0

This update introduces new features.

New features:

• Resume from previous translation.
• Add atomic translation for src-trans inconsistency.

Other Changes:

• Update default whisper model to whisper-large-v3.

v0.2.3

This update improves preprocess efficiency and minor changes.

Other Changes:

• Introduce multiprocessing for loudness normalization.
• Fix the .srt generation issue for video input.
• Add preprocess options, which users can tune.

v0.2.2

This update addresses minor issues.

Other Changes:

• Split audio during noise suppression to avoid out-of-memory.
• Improve translation prompt.

v0.2.1

This update adds a preprocessor to enhance input audio (loudness normalization & noise suppression).

New features:

• Loudness Normalization from ffmpeg-normalize
• Noise Suppression from DeepFilterNet

Other Changes:

• Now all the intermediate files are saved in ./path/to/audio/preprocess.

v0.2.0

This update switch the underlying transcription model from whisperx to faster-whisper, which enable VAD parameter tuning.

New features:

• Switch whisperx back to faster-whisper for VAD parameter tuning.

Other Changes:

• Update translation prompt
  from machinewrapped/gpt-subtrans@82bd2ca.
• Change the default parameters of faster-whisper for consistent transcription.

v0.1.4

This update fixes minor bugs and introduces sentence_split to reduce subtitle length.

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.

v0.1.3

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.

v0.1.2

This update improves the timeline consistency of translated subtitles. Thanks 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.

v0.1.1

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.