Tijs Zwinkels
531418ad07
Interpolate word timestamps based on word character length
2024-02-14 17:01:29 +01:00
Dominik Macháček
2270014219
fixes
2024-02-14 17:01:29 +01:00
Dominik Macháček
f8b2ae07b8
missing features in openai-api, PR #52
2024-02-14 17:01:29 +01:00
Tijs Zwinkels
6ec1f65fe2
Update documentation to include openai-api backend
2024-02-14 17:01:29 +01:00
Tijs Zwinkels
f412812082
OpenAI Whisper API backend
2024-02-14 17:01:29 +01:00
Dominik Macháček
b66c61cf7a
README update auto language detection
2024-02-06 14:31:24 +01:00
Dominik Macháček
cd221a3198
auto language detection #56
2024-02-06 14:29:30 +01:00
Dominik Macháček
1f2352fa1d
README typo and one more simulation option is not shared
2024-01-03 12:52:44 +01:00
Dominik Macháček
bfbe83d792
Samples should be an integer, not seconds
...
- Merge pull request #49 from skripnik/patch-1
- tested performance -- ESIC dev2, 27 docs, on En, De, Cs ASR, Nvidia A40, min chunk 1s, VAD => it has lower WER and latency with "segment" buffer trimming with various thresholds
2024-01-03 10:37:32 +01:00
Aleksei Scripnic
234ac8f5e8
Samples should be an integer, not seconds
...
I believe it's just a typo
2024-01-02 14:40:22 +00:00
Dominik Macháček
aa51e39de4
buffer trimming option, sent. segmenter not required anymore
...
- both for whisper_online + server
- removed argparse code repetition
- README updated
2024-01-02 14:56:30 +01:00
Dominik Macháček
ef08538697
buffer trimming options + most recommendable default
...
evaluated on ESIC dev2, 27 docs
2024-01-02 12:06:29 +01:00
Dominik Macháček
99aef35958
Merge pull request #36 from luweigen/bug-chunk_completed_sentence
...
fix bug of completed sentence chunking. tested on faster-whisper in e…
2023-12-19 13:39:37 +01:00
Dominik Macháček
ff794b4d32
Merge pull request #40 from lifefeel/main
...
Fix: Omitting the last chunk problem in comp_unaware mode
2023-12-07 13:31:47 +01:00
J.P Lee
2b98af7b19
Fix: Omitting the last chunk problem in comp_unaware mode
2023-12-07 17:00:38 +09:00
Dominik Macháček
64c445f073
proceedings link
2023-11-29 10:16:44 +01:00
Dominik Macháček
256ec31d21
bibtex and proceedings link
2023-11-29 10:14:30 +01:00
Wei Lu
a60c64c831
fix bug of completed sentence chunking. tested on faster-whisper in en language
2023-11-28 18:51:36 +02:00
Dominik Macháček
8f32dea5ca
logfile reviewed, whisper_timestamped loading module and vad
...
PR #10 , issues #9 , #30
2023-11-28 12:16:20 +01:00
Dominik Macháček
bd0d848e7f
Merge branch 'main' into TIAGo-WE-COBOT
2023-11-28 11:03:58 +01:00
Dominik Macháček
878f11cdb7
create_tokenizer in documentation
...
#25
2023-11-26 16:11:42 +01:00
Dominik Macháček
483badf85d
Update README.md
...
so many "issues" with question about this :(
2023-11-23 07:41:08 +01:00
Luca
18c1434f77
backend import in child load_model method and expose logfile arg
2023-11-03 11:33:03 +01:00
Luca
f97a253273
Merge branch 'ufal:main' into main
2023-11-03 11:03:54 +01:00
Dominik Macháček
62425111e6
Update README.md
...
slides from oral presentation
2023-11-01 10:30:14 +08:00
Dominik Macháček
4a51e13199
segmenters for all Whisper languages
2023-09-27 23:29:50 +02:00
Luca
6e6b619257
add option to save log to file
2023-09-06 15:19:12 +02:00
Luca
c0dd2e2db9
import backend from __init__
2023-09-06 12:39:26 +02:00
Dominik Macháček
2249846d01
Update README.md
...
paper link
2023-08-02 11:24:50 +02:00
Dominik Macháček
fc74626ff4
demo video on Update README.md
2023-06-28 15:20:56 +02:00
Dominik Macháček
2625be10b7
Ukrainian tokenizer support
2023-06-05 17:29:26 +02:00
Dominik Macháček
260b1f8f88
options readme update, and catch exception in server
2023-06-05 16:26:56 +02:00
Dominik Macháček
e62fba3d82
line packet commited
...
originally from ELITR -- TODO -- change comments
2023-06-02 16:36:06 +02:00
Dominik Macháček
a365074e4b
Update README.md
...
update server description
2023-06-02 11:04:49 +02:00
Dominik Macháček
819ac6c266
server
2023-06-02 10:50:44 +02:00
Dominik Macháček
33369a9555
import WhisperModel
2023-05-25 14:28:18 +02:00
Dominik Macháček
a1ba5e6c3a
updates:
...
- fix errors
- module documented
2023-05-18 17:10:42 +02:00
Dominik Macháček
9310b4f7d8
readme parameter update
2023-05-16 17:45:33 +02:00
Dominik Macháček
88dc796b8a
model_dir, vad and other updates
2023-05-16 17:39:44 +02:00
Dominik Macháček
b1878ce772
offline option
2023-04-20 16:53:45 +02:00
Dominik Macháček
8116b21b4e
faster-whisper support
2023-04-19 15:31:35 +02:00
Dominik Macháček
6dc5cdf330
Update README.md
2023-04-05 12:53:08 +02:00
Dominik Macháček
37fc0f38ca
whisper online
2023-04-05 11:55:24 +02:00
Dominik Macháček
2b5f14dfc3
Initial commit
2023-04-05 11:24:40 +02:00