Commit Graph

58 Commits

Author SHA1 Message Date
Quentin Fuxa
ddb8860528 move files 2025-02-28 18:49:45 +01:00
Quentin Fuxa
00eb4a0a4f UI updated when diarization is disactivated 2025-02-28 18:10:00 +01:00
Quentin Fuxa
2f87e592e0 Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web 2025-02-28 15:44:19 +01:00
Quentin Fuxa
56717b094f DiartDiarization now uses SpeakerSegment 2025-02-28 15:44:09 +01:00
Quentin Fuxa
72ce8d0e3f update frontend for new variables 2025-02-28 15:40:56 +01:00
Quentin Fuxa
09090aa3f5 Add files via upload 2025-02-28 11:49:32 +01:00
Quentin Fuxa
d3960ffef9 Add files via upload 2025-02-28 11:44:29 +01:00
Quentin Fuxa
247582fb33 SpeakerSegment class for future diart improvements 2025-02-26 21:28:22 +01:00
Quentin Fuxa
091d5d7bf5 new buffer format 2025-02-26 21:27:39 +01:00
Quentin Fuxa
9d5d6d8031 UI improvements 2025-02-26 21:26:24 +01:00
Quentin Fuxa
8aa3c760c7 Add files via upload 2025-02-24 09:27:47 +01:00
Quentin Fuxa
2ced4fef20 diarization now works at word - not chunk - level! 2025-02-24 00:35:42 +01:00
Quentin Fuxa
d89622b9c2 Improve sentence tokenization handling - MosesSentenceSplitter now works with list input 2025-02-23 23:41:15 +01:00
Quentin Fuxa
34b707d84e format html and change mapping id <-> speakers 2025-02-23 23:13:18 +01:00
Quentin Fuxa
f200f2cad4 clean diart audiosource class 2025-02-23 23:12:40 +01:00
Quentin Fuxa
09d40a7de8 silence & diarization indicators 2025-02-19 14:42:46 +01:00
Quentin Fuxa
58eba2a1f6 Enhance live transcription UI with improved speaker and silence indicators; add time information display 2025-02-19 14:41:19 +01:00
Quentin Fuxa
1ffa2fa224 add time duration ; display when no speaker is detected 2025-02-19 11:26:30 +01:00
Quentin Fuxa
dc24366580 Number of speakers not anymore limited to 10; a speaker has been created for "being processed" (-1), and another one for no" speaker detected" (-2) 2025-02-19 11:25:59 +01:00
Quentin Fuxa
15089c80fd Add get_buffer method to retrieve unvalidated buffer in string format 2025-02-12 23:36:52 +00:00
Quentin Fuxa
eb989038bd remove useless class that has been replaced by timed_objects 2025-02-07 23:12:54 +01:00
Quentin Fuxa
1f6119e405 all text-related classes now share a common TimedText base class 2025-02-07 23:12:04 +01:00
Quentin Fuxa
b82cc3b613 adapt backend for the new classes 2025-02-07 12:24:37 +01:00
Quentin Fuxa
46f7f9cbd1 Use Sentence, Transcript and ASRToken classes for clarity 2025-02-07 12:24:11 +01:00
Quentin Fuxa
48c111f494 revert changes for segments buffer_trimming_way to work 2025-02-07 10:17:45 +01:00
Quentin Fuxa
54628274d6 show language used 2025-02-07 10:16:46 +01:00
Quentin Fuxa
0d874fb515 cuda or cpu auto detection 2025-02-07 10:16:03 +01:00
Quentin Fuxa
4d1aa4421a Merge pull request #30 from SilasK/tsw
Time stamped text classes
2025-01-31 22:54:58 +01:00
Silas Kieser
15205f31d1 add doctest 2025-01-28 23:17:21 +01:00
Silas Kieser
b1f7034577 my version of timestamped text 2025-01-28 23:13:15 +01:00
Silas Kieser
23dee02d56 sentence overflow works 2025-01-28 22:38:55 +01:00
Silas Kieser
efd80095a7 segment also works 2025-01-28 22:11:28 +01:00
Silas Kieser
611d33cba5 keep a test script in base directory 2025-01-28 17:13:03 +01:00
Silas Kieser
ab7c22d3e3 whisper_online works with the new sentence segment 2025-01-28 17:02:21 +01:00
Silas Kieser
870a779666 sentence work again! 2025-01-28 16:55:07 +01:00
Quentin Fuxa
4622fe7aff Merge branch 'main' into fix-sentencesegmenter 2025-01-28 15:53:10 +01:00
Silas Kieser
8ee1488c08 rename to_flush to concatenate_tsw 2025-01-27 16:49:22 +01:00
Silas Kieser
77d43885a3 chunk at sentence takes now an argument =self.comited 2025-01-27 16:29:06 +01:00
Silas Kieser
04170153e0 improve logging 2025-01-27 16:12:30 +01:00
Silas Kieser
baddf0284b buffer length in sentence segmentation is no also max as in segment. 2025-01-27 15:36:19 +01:00
Quentin Fuxa
6e0f1dda25 Merge remote-tracking branch 'contrib/fix-sentencesegmenter' 2025-01-26 15:34:41 +01:00
Quentin Fuxa
c66794e1f5 Merge pull request #20 from SilasK/clean-main
In my limited experience with french "" should also be the sep for mlx-whisper
2025-01-26 14:57:52 +01:00
Silas Kieser
f0eaffacd3 improve logging in whisper_online.py 2025-01-21 14:59:36 +01:00
Silas Kieser
9f262813ec sep for mlx is also "" 2025-01-21 12:16:46 +01:00
Silas Kieser
4293580581 use moses sentence segmenter instead of tokenizer 2025-01-21 12:12:41 +01:00
Silas Kieser
42d2784c20 clearer log messages for sentence segmentation 2025-01-21 12:11:54 +01:00
Silas Kieser
7fad0a3ee2 sep for mlx is also "" 2025-01-21 10:42:07 +01:00
Quentin Fuxa
fba37eba0a move to src 2025-01-19 21:17:55 +01:00
Quentin Fuxa
5523b51fd7 first speaker is "0" no more None 2025-01-19 19:40:09 +01:00
Quentin Fuxa
9bdb92e923 update demo.png 2025-01-19 19:36:10 +01:00