v0.7.0
版本发布时间: 2023-07-18 21:30:31
SYSTRAN/faster-whisper最新发布版本:v1.0.3(2024-07-01 18:05:08)
Improve word-level timestamps heuristics
Some recent improvements from openai-whisper are ported to faster-whisper:
- Squash long words at window and sentence boundaries (https://github.com/openai/whisper/commit/255887f219e6b632bc1a6aac1caf28eecfca1bac)
- Improve timestamp heuristics (https://github.com/openai/whisper/commit/f572f2161ba831bae131364c3bffdead7af6d210)
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 https://github.com/openai/whisper/commit/e334ff141d5444fbf6904edaaf408e5b0b416fe8) - 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