5e46825474
Add try/catch wrapper for C++ method to raise native exceptions. Python and Java
...
are implemented, others on the way
2021-10-12 22:31:36 +02:00
fcab5a9581
Revert CFFI bump
2021-10-10 22:09:55 +02:00
e7f5e0ac23
Bump cffi version
2021-10-10 21:21:32 +02:00
e2af710369
Rework rescoring for faster and more accurate results
2021-08-31 21:56:21 +02:00
2349e66a97
Subtitles require word times ( #607 )
...
This is a port of the recent addition of commit 7ccf743
2021-06-27 18:06:11 +03:00
02ef49f67e
Allow Saving WebVTT ( #605 )
...
This patch is a small extension to the WebVTT example which allows to
directly save the WebVTT output to a file like this:
./test_webvtt.py test.wav out.vtt
2021-06-24 19:35:30 +03:00
7cdf8f1d03
Add Python WebVTT Example ( #601 )
...
This patch adds an example for using webvtt-py to generate WebVTT files
from Vosk output. This is similar to the SRT example but still very
useful for generating an example video subtitle usable in web contexts.
2021-06-23 01:16:33 +03:00
7ccf743bb6
SRT requires word times
2021-06-10 10:37:15 +02:00
75bedfe06d
Add a method to show/hide words and their times
2021-06-07 01:04:37 +02:00
4ea9885d44
Bump version
2021-05-30 21:59:46 +02:00
6aa5af7640
Add reset test
2021-05-26 21:22:07 +02:00
499b2f183a
Introduce new API to set speaker model to already initialized recognizer.
...
Introduce a method to reset recognizer results to start from scratch without
computation of the result.
2021-05-26 00:46:32 +02:00
f8189685e5
Add max alternatives output
2021-05-19 18:47:25 +02:00
ee8663e6d9
RNNLM rescoring support
2021-05-05 19:34:30 +02:00
77abb02ada
Bump version
2021-04-12 12:23:11 +02:00
a5a3697b7c
Copy data before queue, original data can be destroyed.
...
Fixes issue #444
Thanks to Alexander Zatvornitsky
2021-03-01 21:25:41 +01:00
eea7ca571b
- Added an optional HAVE_CUDA flag to build Vosk with GPU support.
...
- Added missing GpuInit/ThreadInit python wrappers.
2021-02-22 12:30:46 +02:00
db3e31d7ce
Automatically put .so file in resources
2021-02-16 17:33:09 +01:00
d917af21ab
Better search for Windows dlls
2021-02-12 22:24:54 +01:00
c6119c4835
test_microphone: AcceptWavform wants bytes
2021-02-08 00:38:28 +02:00
7a75e1c3f4
Add arm architectures
2021-02-07 20:28:14 +01:00
c3430e448a
Add build for Windows wheel
2021-02-07 18:11:38 +01:00
02dc0ce0c8
Take source location from environment
2021-02-07 15:17:35 +01:00
15697a18e8
Platform-specific wheel
2021-02-07 14:58:10 +01:00
481881e59d
Fully move python to cffi
2021-02-07 13:23:03 +01:00
11a25b26a7
Add cffi wrapper
2021-02-07 10:57:57 +01:00
6e861c6a19
Add nuget platforms
2021-02-05 00:39:27 +01:00
fe91b5a717
Preprocess header on the fly
2021-01-10 21:11:35 +01:00
a052506a5d
Add cffi example
2021-01-10 20:53:43 +01:00
6f2d6d0d69
Proper microphone recognizer with the queue
2021-01-09 23:16:35 +01:00
1b8332a609
Raise to 0.3.17
2021-01-09 02:29:56 +01:00
9d398eff0e
Remove armv6, too slow anyway. Build with new dockcross.
2021-01-06 16:26:23 +01:00
02b7312a00
Build with openblas-clapack to avoid fortran
2021-01-06 01:11:03 +01:00
08c35e84f3
Update demo with spk vector check
2020-12-23 22:21:12 +01:00
b92a5c1fc7
Update wheels to openfst 1.8.0
2020-12-22 23:27:01 +01:00
8997a587c5
Fix warnings in preparation for openfst 1.8.0
2020-12-22 21:16:20 +01:00
dc3d03d742
Make sure we have result field in json
2020-11-29 19:19:50 +01:00
84df40715c
Add Filipino
2020-11-19 14:53:46 +01:00
746ff47757
Split long lines in subtitles
2020-11-03 15:13:16 +01:00
0269a10833
Critical ivector bugfix and version 0.3.15
2020-10-13 01:28:46 +02:00
7af3e9a334
Add srt example
2020-10-07 13:43:09 +02:00
d666876be1
Revert compile flags
2020-10-05 01:24:32 +02:00
d43cbe9344
Add 0.3.14
2020-10-04 23:45:34 +02:00
57cc474c9f
Build bigram language model from grammars
2020-10-04 23:42:50 +02:00
586603f8e1
Add Farsi
2020-10-03 12:42:54 +02:00
d57887d22a
Add Greek
2020-09-30 13:42:20 +02:00
6183bcfc5f
Add Arabic model
2020-09-30 13:29:43 +02:00
65f6113b4d
Add Catalan
2020-09-27 11:57:20 +02:00
62885e8963
Update descriptions
2020-09-22 11:30:27 +02:00
f97383c17f
Update models location
2020-09-22 00:00:24 +02:00
Nickolay Shmyrev