Tags: clamsproject/app-whisper-wrapper
Tags
- Now based on whisper 240930 version with support of `turbo` model - Beam search size is set to 5 for the decoder, following the `whisper` command's default - (temporarily) Disabled multiprocessing web app via gunicorn and fell back to flask built-in to work around CUDA memory issue
This version adds some delegation parameters to whisper.transcribe - `task`: delegate to `--task` - `initialPrompt`: delegate to `--initial-prompt` - `conditionOnPreviousText`: delegate to `--condition-on-previous-text` - `noSpeechThreshold`: delegate to `--no-speech-threshold`
This version include addition of `modelLang` param and many other cha… …nges * **(BIG CHANGE)** timeunit is now millisecond (integer) * `modelLang` parameter is added for selecting language to instruct Whisper to use, Whisper will run in language detection mode if this parameter is not given. * When `modelLang` is set to `en`, load english only models instead of multilingual ones for speed and performance * skips empty segments from whisper when generating output MMIF * updated to clams-python 1.1.1
PreviousNext