Download Latest Version faster-whisper 1.2.1 source code.tar.gz (21.4 MB)
Email in envelope

Get an email when there's a new version of Faster Whisper

Home / v1.1.0
Name Modified Size InfoDownloads / Week
Parent folder
faster-whisper 1.1.0 source code.tar.gz 2024-11-21 21.4 MB
0
faster-whisper 1.1.0 source code.zip 2024-11-21 21.4 MB
0
README.md 2024-11-21 1.9 kB
0
Totals: 3 Items   42.8 MB 0

New Features

  • New batched inference that is 4x faster and accurate, Refer to README on usage instructions.
  • Support for the new large-v3-turbo model.
  • VAD filter is now 3x faster on CPU.
  • Feature Extraction is now 3x faster.
  • Added log_progress to WhisperModel.transcribe to print transcription progress.
  • Added multilingual option to transcription to allow transcribing multilingual audio. Note that Large models already have codeswitching capabilities, so this is mostly beneficial to medium model or smaller.
  • WhisperModel.detect_language now has the option to use VAD filter and improved language detection using language_detection_segments and language_detection_threshold.

Bug Fixes

  • Use correct features padding for encoder input when chunk_length <30s
  • Use correct seek value in output

Other Changes

  • replace NamedTuple with dataclass in Word, Segment, TranscriptionOptions, TranscriptionInfo, and VadOptions, this allows conversion to json without nesting. Note that _asdict() method is still available in Word and Segment classes for backward compatibility but will be removed in the next release, you can use dataclasses.asdict() instead.
  • Added new tests for development
  • Updated benchmarks in the Readme
  • use jiwer instead of evaluate in benchmarks
  • Filter out non_speech_tokens in suppressed tokens by @jordimas in https://github.com/SYSTRAN/faster-whisper/pull/898

New Contributors

Full Changelog: https://github.com/SYSTRAN/faster-whisper/compare/v1.0.3...v1.1.0

Source: README.md, updated 2024-11-21