script to lib

Merge pull request #91 from QuentinFuxa/refacto_lib

Refactor import statement for AudioProcessor and update cleanup method to be awaited; remove unused formatters and state management files

Refactor AudioProcessor methods for improved async handling and WebSocket integration

Refactor DiartDiarization initialization and streamline WebSocket audio processing

refacto 0

Refactor PCM conversion to a dedicated function; immediate chunk addition to the diarization queue

Update README.md

Merge pull request #85 from SilasK/warm-up

Warmup functionality: add timeout option (for VM not connected to internet); False option to disable warmup

Create CONTRIBUTING.md

fix #84

Diarization : Uses a rx observer instead of diart attach_hooks method

change default model to tiny, and vad activated by default

Update README.md

recording duration & waveform added

use confidence scores returned by whisper to immediately validate tokens

update font

ffmpeg timout from 5 to 15s; diarization lag does not stay = 0 at the beginning

update demo

clean html

Update README.md

Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web

solve https://github.com/QuentinFuxa/whisper_streaming_web/issues/60#issuecomment-2692191781

huggingface steps added. Solve https://github.com/QuentinFuxa/whisper_streaming_web/issues/59 & https://github.com/QuentinFuxa/whisper_streaming_web/issues/60

Delete src directory

src/web to web

move files

split backends and online asr files

add coming soon

update import paths

time objects is now used by DiartDiarization class

silero vad

undiarized text is assigned to last speaker, with buffer information; traceback is used to format_exc errors

UI updated when diarization is disactivated

Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web

DiartDiarization now uses SpeakerSegment

// execution for diarization and transcription

update frontend for new variables

Add files via upload

Add files via upload

SpeakerSegment class for future diart improvements

new buffer format

UI improvements

Add files via upload

Merge pull request #57 from QuentinFuxa/diart_integration_improvements

diarization now works at word - not chunk - level!

Merge pull request #56 from QuentinFuxa/diart_integration_improvements

Improve sentence tokenization handling - MosesSentenceSplitter now works with list input

Merge pull request #55 from QuentinFuxa/diart_integration_improvements