faster-whisper 0.7.0
Improve word-level timestamps heuristics
Some recent improvements from openai-whisper are ported to faster-whisper:
- Squash long words at window and sentence boundaries (openai/whisper@255887f)
- Improve timestamp heuristics (openai/whisper@f572f21)
Support download of user converted models from the Hugging Face Hub
The WhisperModel
constructor now accepts any repository ID as argument, for example:
model = WhisperModel("username/whisper-large-v2-ct2")
The utility function download_model
has been updated similarly.
Other changes
- Accept an iterable of token IDs for the argument
initial_prompt
(useful to include timestamp tokens in the prompt) - Avoid computing higher temperatures when
no_speech_threshold
is met (same as openai/whisper@e334ff1) - Fix truncated output when using a prefix without disabling timestamps
- Update the minimum required CTranslate2 version to 3.17.0 to include the latest fixes