faster-whisper 1.1.0

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 #898

New Contributors

• @Jiltseb made their first contribution in #856
• @heimoshuiyu made their first contribution in #1092

Full Changelog: v1.0.3...v1.1.0

faster-whisper 1.0.3

Upgrade Silero-Vad model to latest V5 version (#884)

Silero-vad V5 release: https://github.com/snakers4/silero-vad/releases/tag/v5.0

• window_size_samples parameter is fixed at 512.
• Change to use the state variable instead of the existing h and c variables.
• Slightly changed internal logic, now some context (part of previous chunk) is passed along with the current chunk.
• Change the dimensions of the state variable from 64 to 128.
• Replace ONNX file with V5 version

Other changes

• Improve language detection when using clip_timestamps (#867)
• Docker file improvements (#848)
• Fix #839 incorrect clip_timestamps being used in model (#842)

faster-whisper 1.0.2

• Add support for distil-large-v3 (#755)
  The latest Distil-Whisper model, distil-large-v3, is intrinsically designed to work with the OpenAI sequential algorithm.

• Benchmarks (#773)
  Introduces functionality to measure benchmarking for memory, Word Error Rate (WER), and speed in Faster-whisper.

• Support initializing more whisper model args (#807)

• Small bug fix:

  • code breaks if audio is empty (#768)
  • Foolproof: Disable VAD if clip_timestamps is in use (#769)
  • make faster_whisper.assets as a valid python package to distribute (#774)
  • Loosen tokenizers version constraint (#804)
  • CUDA version and updated installation instructions (#785)

• New feature from original openai Whisper project:

  • Feature/add hotwords (#731)
  • Improve language detection (#732)

faster-whisper 1.0.1

• Bug fixes and performance improvements:
  • Update logic to get segment from features before encoding (#705)
  • Fix window end heuristic for hallucination_silence_threshold (#706)

faster-whisper 1.0.0

• Support distil-whisper model (#557)
  Robust knowledge distillation of the Whisper model via large-scale pseudo-labelling.
  For more detail: https://github.com/huggingface/distil-whisper

• Upgrade ctranslate2 version to 4.0 to support CUDA 12 (#694)

• Upgrade PyAV version to 11.* to support Python3.12.x (#679)

• Small bug fixes

  • Illogical "Avoid computing higher temperatures on no_speech" (#652)
  • broken prompt_reset_on_temperature (#604)
  • Word timing tweaks (#616)

• New improvements from original OpenAI Whisper project

  • Skip silence around hallucinations (#646)
  • Prevent infinite loop for out-of-bound timestamps in clip_timestamps (#697)

faster-whisper 0.10.1

Fix the broken tag v0.10.0

faster-whisper 0.10.0

• Support "large-v3" model with
  • The ability to load feature_size/num_mels and other from preprocessor_config.json
  • A new language token for Cantonese (yue)
• Update CTranslate2 requirement to include the latest version 3.22.0
• Update tokenizers requirement to include the latest version 0.15
• Change the hub to fetch models from Systran organization

faster-whisper 0.9.0

• Add function faster_whisper.available_models() to list the available model sizes
• Add model property supported_languages to list the languages accepted by the model
• Improve error message for invalid task and language parameters
• Update tokenizers requirement to include the latest version 0.14

faster-whisper 0.8.0

Expose new transcription options

Some generation parameters that were available in the CTranslate2 API but not exposed in faster-whisper:

• repetition_penalty to penalize the score of previously generated tokens (set > 1 to penalize)
• no_repeat_ngram_size to prevent repetitions of ngrams with this size

Some values that were previously hardcoded in the transcription method:

• prompt_reset_on_temperature to configure after which temperature fallback step the prompt with the previous text should be reset (default value is 0.5)

Other changes

• Fix a possible memory leak when decoding audio with PyAV by forcing the garbage collector to run
• Add property duration_after_vad in the returned TranscriptionInfo object
• Add "large" alias for the "large-v2" model
• Log a warning when the model is English-only but the language parameter is set to something else

faster-whisper 0.7.1

• Fix a bug related to no_speech_threshold: when the threshold was met for a segment, the next 30-second window reused the same encoder output and was also considered as non speech
• Improve selection of the final result when all temperature fallbacks failed by returning the result with the best log probability