DEV/alphacep_vosk-api
1
0
Fork 0
mirror of https://github.com/alphacep/vosk-api.git synced 2026-02-05 12:59:27 +08:00
Code Issues Packages Projects Releases Wiki Activity
197 Commits 4 Branches 30 Tags
Commit Graph

57 Commits

Author SHA1 Message Date
Nickolay Shmyrev
d43cbe9344 Add 0.3.14 2020-10-04 23:45:34 +02:00
Nickolay Shmyrev
57cc474c9f Build bigram language model from grammars 2020-10-04 23:42:50 +02:00
Nickolay Shmyrev
586603f8e1 Add Farsi 2020-10-03 12:42:54 +02:00
Nickolay Shmyrev
d57887d22a Add Greek 2020-09-30 13:42:20 +02:00
Nickolay Shmyrev
6183bcfc5f Add Arabic model 2020-09-30 13:29:43 +02:00
Nickolay Shmyrev
65f6113b4d Add Catalan 2020-09-27 11:57:20 +02:00
Nickolay Shmyrev
62885e8963 Update descriptions 2020-09-22 11:30:27 +02:00
Nickolay Shmyrev
f97383c17f Update models location 2020-09-22 00:00:24 +02:00
Nickolay Shmyrev
4b892ec5e7 Bump version 2020-09-21 23:49:55 +02:00
Nickolay Shmyrev
41035485db Fix x-vectors, now they actually work. Requires new version spk-model-0.4 with whitening transform matrix 2020-09-21 23:31:30 +02:00
Nickolay Shmyrev
55abf5f5ac Dynamic arch in pip module 2020-09-13 22:08:36 +02:00
Nickolay Shmyrev
1c7b94757d Don't attempt to resize to empty matrix 2020-07-31 16:45:05 +02:00
Nickolay Shmyrev
8a986ef384 Require KALDI_MKL to be 1 2020-07-12 11:03:22 +02:00
Nickolay Shmyrev
722b09eaa4 Ignore words missing in the vocabulary 2020-07-08 01:35:50 +02:00
Nickolay Shmyrev
4407d8da55 Another timestamp bugfix 2020-07-08 01:35:50 +02:00
Nickolay Shmyrev
f6c115d215 Update to 0.3.9 and use our fork of openfst based on openfst 1.7.7 2020-06-16 19:13:57 +02:00
Nickolay Shmyrev
b81f69d407 Avoid overflow. See issue #128 2020-06-06 10:43:44 +02:00
Nickolay Shmyrev
1d00bd244e Multithreaded testing 2020-06-06 00:40:15 +02:00
Nickolay Shmyrev
75993ea276 Update to 0.3.8 2020-06-01 00:55:28 +02:00
Nickolay Shmyrev
b1e775c67b Better speaker identification without silence frames 2020-05-31 23:46:42 +02:00
Nickolay Shmyrev
31bb0557d9 Add mkl support 2020-05-30 23:22:14 +02:00
Nickolay Shmyrev
25aadf61bc Fix travis 2020-05-09 17:36:55 +02:00
Nickolay Shmyrev
be47056467 Updates for osx 2020-05-09 15:49:24 +03:00
Nickolay Shmyrev
8f623e0aea Get rid of broken cmake 2020-05-09 14:32:46 +02:00
Nickolay Shmyrev
910455802e Don't link to the library explicitely to allow relocations 2020-05-08 15:16:50 +03:00
Nickolay Shmyrev
dfe11eaf83 Linux build fix 2020-05-08 09:04:14 +02:00
Nickolay Shmyrev
37fbe1a52b OSX build 2020-05-08 09:55:15 +03:00
Nickolay Shmyrev
af11bb2361 No need for external dependencies 2020-05-07 21:48:03 +02:00
Nickolay Shmyrev
8da8697c1e Add ffmpeg test 2020-05-07 21:07:17 +02:00
Nickolay Shmyrev
5c4dd4644e Update version 2020-05-03 20:52:43 +02:00
Nickolay Shmyrev
80219066e9 Expose verbose level in the API 2020-05-01 19:02:57 +02:00
Nickolay Shmyrev
d75bb36131 Fix model download path 2020-04-30 11:04:35 +02:00
Nickolay Shmyrev
80e60b9118 LM Rescoring 2020-04-28 22:17:34 +02:00
Nickolay Shmyrev
86caf526f5 New model layout and model config file with beams for decoding 2020-04-28 01:06:41 +02:00
Nickolay Shmyrev
3803ab345d Proper reference couting of the models to avoid memory issus 2020-04-23 23:37:52 +02:00
Nickolay Shmyrev
ffd810fe00 Fix threading bug 2020-04-22 22:15:45 +02:00
Nickolay Shmyrev
6f3190d83d Version 0.3.4 and arm wheels for python 3.6 2020-04-21 11:38:56 +02:00
Nickolay Shmyrev
feffb2711d Repair travis build 2020-04-04 20:49:06 +02:00
Nickolay Shmyrev
df9424a228 Introduce pure C api to deal with Windows runtime issues and make it easy to wrap in Swift 2020-04-04 00:35:56 +02:00
André Mendes
14b2c13ed6 Fixes folder name instruction for python model on microphone test 2020-03-25 01:01:23 -03:00
Nickolay Shmyrev
6b787a4d1e We actually need a bit newer cmake 2020-02-27 00:43:03 +01:00
Nickolay Shmyrev
095fac1de4 Small unittest 2020-02-25 21:45:27 +01:00
Nickolay Shmyrev
8913b93703 Fix message 2020-02-23 16:05:34 +00:00
Nickolay Shmyrev
7e44844cd5 Added dockcross images for arm builds 2020-02-23 10:19:31 +01:00
Nickolay Shmyrev
f66f7a9290 Added microphone test 2020-02-21 00:08:50 +01:00
Nickolay Shmyrev
378fa3499a Downsample by default and also check wav file encoding in examples. Thanks to 
dtreskunov. See for details

https://github.com/alphacep/vosk-api/pull/23
 2020-02-18 11:45:50 +01:00
Nickolay Shmyrev
01eeec498d Fix memory access issues 2020-02-17 09:42:50 +00:00
Nickolay Shmyrev
d422dfbddb Message update 2020-02-16 17:21:38 +01:00
Nickolay Shmyrev
aa91ccf68b Added speaker identification 2020-02-16 17:04:37 +01:00
Nickolay Shmyrev
8c9bae3ad1 Update version for Kaldi rebuild 2020-02-08 23:40:42 +01:00