Quentin Fuxa
|
84b09bb2cc
|
handle ffmpeg timeouts > 5s
|
2025-02-14 17:22:03 +00:00 |
|
Quentin Fuxa
|
15089c80fd
|
Add get_buffer method to retrieve unvalidated buffer in string format
|
2025-02-12 23:36:52 +00:00 |
|
Quentin Fuxa
|
788fe1c676
|
optimize ffmpeg buffer reading :round duration to nearest lower 0.1s
|
2025-02-12 23:28:58 +00:00 |
|
Quentin Fuxa
|
d623578d95
|
Merge pull request #43 from QuentinFuxa/load-the-model-just-once
Load the model just once
|
2025-02-12 05:54:38 +01:00 |
|
Quentin Fuxa
|
149d2ee44c
|
Use lifespan to load the model just one
|
2025-02-12 05:53:55 +01:00 |
|
Quentin Fuxa
|
adaca751ce
|
remove logs handler
|
2025-02-12 05:46:56 +01:00 |
|
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remove useless class that has been replaced by timed_objects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
|
f7f1f259c1
|
buffer is now transcript.text
|
2025-02-07 12:25:05 +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 |
|
Quentin Fuxa
|
f4d98e2c8c
|
Merge pull request #27 from SilasK/fix-sentencesegmenter
Fix sentence segmenter
|
2025-01-31 22:54:33 +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
|
f4d3df3d87
|
change log format
|
2025-01-28 21:25:17 +01:00 |
|
Silas Kieser
|
9c7d429e15
|
add logging config to server
|
2025-01-28 17:38:13 +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
|
c3d72cae7c
|
Merge pull request #26 from SilasK/fix-sentencesegmenter
Improve logging stil trying to fix sentence segmenter
|
2025-01-28 15:53:26 +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
|
69a2ed6bfb
|
add logger for online asr
|
2025-01-21 14:45:45 +01:00 |
|
Silas Kieser
|
25eb276794
|
ignore wav and scripts
|
2025-01-21 14:08:41 +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
|
27d2db77f7
|
Update README.md
|
2025-01-20 03:08:01 +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 |
|
Quentin Fuxa
|
b51c8427f4
|
diart link added
|
2025-01-19 17:12:55 +01:00 |
|
Quentin Fuxa
|
977436622a
|
add diarization (beta). Disabled by default
|
2025-01-19 17:12:40 +01:00 |
|
Quentin Fuxa
|
ce56264241
|
split whisper_online.py into smaller files
|
2025-01-14 20:52:53 +01:00 |
|
Quentin Fuxa
|
9cbac96c44
|
del online once webstreaming is finished
|
2025-01-14 20:20:22 +01:00 |
|
Quentin Fuxa
|
3f30d3de6e
|
Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web
|
2025-01-14 20:14:22 +01:00 |
|
Quentin Fuxa
|
f884d1162d
|
warning when transcribe_kargs are used with MLX Whisper
|
2025-01-14 20:14:16 +01:00 |
|