Tom Boccuto
e61c01d496
Use unordered_set for nonsilence lookup in GetSpkVector ( #2035 )
...
Replaces O(n^2) std::find scan with O(1)-avg hash-set lookup,
addressing the existing "would be nice to have faster search"
comment. Total cost drops from O(num_frames * |nonsilence|) to
O(num_frames + |nonsilence|).
2026-07-02 23:03:34 +03:00
Kevin Brown
3bc886a6c4
Add SpeechService constructor accepting a caller-supplied AudioRecord ( #2044 )
...
Allows callers to control the audio input device - for example, to pin
recording to the built-in microphone when an external USB camera without
a microphone causes Android to silently select the wrong input source.
The new overload (Recognizer, float, AudioRecord) mirrors the existing
(Recognizer, float) signature. Ownership semantics differ: the caller
supplies and owns the recorder, so on failure this constructor throws
without releasing it, leaving cleanup to the caller.
Co-authored-by: Kevin Brown <git@whidit.com >
2026-06-04 20:54:55 +03:00
Kevin Brown
e81a422289
Add getAudioSessionId() getter to SpeechService ( #2042 )
...
Expose the AudioRecord session ID so callers can attach Android audio
effects (e.g. NoiseSuppressor, AcousticEchoCanceler) to the recording
session without subclassing or reflection.
Co-authored-by: Kevin Brown <git@whidit.com >
2026-05-29 08:50:13 +03:00
Vladimir Ulianitsky
9adbd76c77
Add Ruby gem ( #2022 )
...
* Init gem
* WIP
* WIP
* WIP: Gemify
* WIP
* Try ffi_gen
* Revert "Try ffi_gen"
This reverts commit a54e56b35a1bdc079dbe122aff47d79038d4e52f.
* Vibecode 1
* Vibecode 2
* rework progressbar
* Some ref + test_captcha
* Return deleted by Claude
* Draft precompiled packaging
* Review and refactor C bindings
* ref OwnedString
* Rename methods and add notes
* rubocop
* Fix progressbar, add examples
* Ref spec
* Ref spec - final
* Final ver
* Add srt, other fixes
* Move to ruby dir
---------
Co-authored-by: Nickolay V. Shmyrev <nshmyrev@gmail.com >
2026-02-22 11:51:10 +03:00
Nickolay Shmyrev
625e44c626
Bump JNA requirements to 5.18.1 and update version
2025-12-08 21:47:46 +01:00
Nickolay Shmyrev
488fc44d71
Add missing file to git, fixes #2001
2025-10-24 13:10:51 +02:00
Adam Jaso
a428d65966
Add Golang GPU Batch API and example ( #1983 )
...
Co-authored-by: ajaso <github@ajaso.net >
2025-09-10 16:13:51 +03:00
Nickolay Shmyrev
056a2ad548
Updates for recent android
2025-09-03 09:46:07 +02:00
Nickolay Shmyrev
07a0ddb467
Add endpointer mode to java and csharp API
2025-09-03 07:14:40 +02:00
resignedScientist
24f0e0cff8
add 16 KB page size support ( #1976 )
...
Co-authored-by: Norman Laudien <kontakt@norman-laudien.de >
2025-08-25 02:08:01 +03:00
Utkarsh Gual
0f364e3a44
Fix typo in encoding in transcribe_scp.py ( #1955 )
...
Fix typo in encoding in transcribe_scp.py. uft-8 -> utf-8
2025-07-11 23:02:00 +03:00
Nickolay Shmyrev
eabd80a848
Support MUSL variant in packging
2025-05-01 11:20:40 +02:00
Nickolay Shmyrev
780ba2f0b7
Add MUSL build
2025-05-01 11:06:56 +02:00
Nickolay Shmyrev
47509f7f9c
Properly rebuilt fst
2025-05-01 09:05:17 +02:00
Md Husain Thekiya
4bf3370826
Fix: Raise exception in Node.js binding when model creation fails ( #716 ) ( #1714 )
2025-03-05 19:16:56 +03:00
Matt Kenefick
cf67ed6cd9
Support ARM 64 in NodeJS ( #1655 )
...
Identify and support ARM64 in the NodeJS vosk-api
2024-11-14 00:23:16 +03:00
Nickolay Shmyrev
0979c46766
Add speaker vector to n-best results. Fixes issue #1647
2024-10-24 15:34:05 +02:00
Nickolay V. Shmyrev
eeab22ed98
Added postprocessor. Fixes #1641
2024-10-11 00:05:08 +03:00
Paschalis M
a9f27eb11d
Update README.md with training details ( #1637 )
2024-09-26 16:29:42 +03:00
Nickolay Shmyrev
1b308a3017
Added Win ARM64 build
2024-08-23 21:36:40 +02:00
Nickolay Shmyrev
f5540085b5
Add text processor wrapper for java
2024-08-22 03:13:44 +02:00
Clocks
c64c3daa3b
Kotlin updates ( #1596 )
...
* Add TextProcessor.kt
* Add Recognizer end pointer functions
* Properly close input stream
Mirror of 5d09ee8
* Bump android compile sdk to 34
* Update everything
All dependencies, etc
2024-06-19 22:22:50 +03:00
Nickolay Shmyrev
cc48ff9567
Properly count active states
2024-06-17 07:24:51 +02:00
johngebbie
7358c799b1
go: Add SetEndpointerDelays ( #1570 )
2024-05-06 08:33:26 +03:00
Nickolay Shmyrev
a7bf6a51e2
Bump version
2024-04-22 14:39:57 +02:00
Nickolay Shmyrev
72797111db
Fix timeouts for endpointer
2024-04-22 14:29:39 +02:00
__Rylex__
40937b6bcb
Kaldi remove lm target because rnnlm has lm ( #1543 )
...
* Update Dockerfile.win
* Update Dockerfile.dockcross
* Update Dockerfile.manylinux
* Update Dockerfile.dockcross-manylinux
* Update Dockerfile.manylinux-mkl
* Update Dockerfile.win32
* Update build-vosk.sh
2024-04-01 15:58:09 +03:00
Nickolay Shmyrev
7da70c6107
Add test for ITN
2024-03-29 12:57:01 +01:00
Nickolay Shmyrev
2426225d74
Add postprocessor
2024-03-29 12:44:54 +01:00
Nickolay V. Shmyrev
c4d32a2293
Inverse text normalization with FSTs ( #1545 )
...
* Add ITN from Wetext
2024-03-29 14:32:05 +03:00
__Rylex__
6f7fe0e417
fix typp ( #1519 )
2024-02-21 11:00:19 +03:00
Nickolay Shmyrev
aba84973b1
Update to latest gradio
2023-12-15 00:23:37 +01:00
Nickolay Shmyrev
339b1c5d00
Fix t_max endpointer config and introduce t_start_max for silent inputs.
2023-12-13 04:45:30 +01:00
Nickolay Shmyrev
a35728fa67
Simplify server argument
2023-11-27 15:40:58 +01:00
Nickolay Shmyrev
322a57b512
Fix json output format
2023-11-27 15:39:49 +01:00
Gonzalo
a21d1ad051
feat: enable usage of remote server and not only localhost ( #1375 )
2023-11-27 17:22:59 +03:00
Nickolay Shmyrev
a47fa9147b
Add endpointer delays parameter
2023-11-27 15:29:31 +01:00
Wire
dfb76f0126
go: do not include libdl if building on Windows ( #1464 )
2023-11-12 01:26:17 +03:00
Nickolay Shmyrev
c3e3fc002f
Add online endpointer reconfiguration
2023-10-16 13:40:32 +02:00
Nickolay Shmyrev
62fc308bdf
Sometimes python interpreter destroys the handle on exit before
...
the object. See
https://foss.heptapod.net/pypy/cffi/-/issues/340
2023-09-04 00:33:42 +02:00
Dmitri Soloviev
60c0e33901
simplify go example ( #1430 )
2023-08-12 23:04:46 +03:00
jsbxyyx
5d09ee8b2b
close source input stream ( #1 ) ( #1428 )
2023-08-11 00:55:33 +03:00
JohnGebbie
12f29a3415
go: Add SetGrm ( #1346 )
2023-04-29 05:35:01 +03:00
Nickolay Shmyrev
d56221bcf2
Add mkl docker build
2023-04-06 02:38:06 +02:00
Nickolay Shmyrev
a2eb39d2d7
Set number of MKL threads
2023-04-06 02:10:53 +02:00
Anton Romanov
128c216c61
Fix vosk-transcriber cli json format ( #1304 )
...
Fix error UnboundLocalError: local variable 'monologue' referenced before assignment in transcriber.py line 102
2023-03-29 03:12:16 +03:00
mason-acronode
da87d0dad3
c# supports GPU inference ( #1307 )
...
* Added Batch P/Invoke to be able to use GPU based inference
* Modified Result method
* Modified Result method
* Fixed code to call BatchModel
---------
Co-authored-by: minsik.sim <minsik.sim@cyara.com >
2023-03-25 12:28:14 +03:00
Nickolay Shmyrev
9cee2899bb
Update publishing plugin and simplify gradle build
2023-03-15 22:50:42 +01:00
Doomsdayrs
a40742bbaf
Kotlin: Numerous Improvements ( #1274 )
...
* kotlin: bump version for future release
* kotlin: Unify dependency versions
* kotlin: Add AUTHORS
* kotlin: Add MAINTENANCE.md
* kotlin: Add README.md
* kotlin: Update common/Vosk.kt documentation
* kotlin: Fix indentation in build.gradle.kts
* kotlin: Add .idea files to unify how IDEs work
* kotlin: Reformat all code
* kotlin: Update all code headers
* kotlin: Add @JvmStatic to objects
* kotlin: Use Consumer instead of Kotlin lambda in StorageService.kt
* kotlin: Annotate SpeechService.kt as throwing IOException
* kotlin: Add gradle migration settings
* kotlin: Add Deprecated annotation to jvm/LibVosk.setLogLevel
* kotlin: Overhaul exceptions
* Update documentation
* Add function for creating a Recognizer with a proper list
* Update documentation
2023-03-03 19:12:54 +03:00
Doomsdayrs
d714dff8d3
Add Kotlin Multiplatform ( #1241 )
...
* Init
* Implement common
* Implement JVM target
* Ignore build/ directory
* Implement android
* Disable kotlin/native targets
* Remove jCenter()
* Upgrade android tools to 7.3.0
* Enforce not null for essential windows operations
* Add license headers
* Add maven-publish
* Add dokka for javadoc
* Add disabled kotlin/native for linux
This is disabled currently due to vosk
not having a proper installation method on linux yet.
* Add empty constructors for JVM classes
* Fix library initialization for JVM
* Add DecoderDemo
* Add serialization support
* Convert no arg functions with returns to val properties
* Properly implement DecoderTest
* Import other android classes
* Properly name json parser as voskJson
* Add license headers to native target
* Unify free functions with Freeable interface
This makes it easy for Kotlin/Native to use a "use" function to
auto free after use of a Freeable.
* Document JVM default constructor
* Add JVM specific constructors with NIO/IO
* Inline default constructors in Common
* Properly handle invalid paths
* Add android publishing block
* Merge serialization into common
* Update to Kotlin 1.8.10
* Update to JNA 5.13.0
* Put native target behind environment variable or override.
Due to a lack of official packaging,
this is not possible currently.
* Properly handle Recognizer.acceptWaveform exceptions
* Add flow extension for converting (InputStream->Recognizer) to a flow.
* Use ByteFlow for waveform flow instead.
This allows custom readers, and more advanced backends,
such as the Dicio example in DecoderTest.kt .
2023-02-17 03:47:20 +03:00
Nickolay Shmyrev
790c564d14
Ignore non-audio files in folder transcription
2023-02-10 00:57:14 +01:00
Nickolay Shmyrev
988ba3f257
Bump JNA dependency everywhere
2023-02-08 22:55:22 +01:00
Nickolay Shmyrev
2796da0a50
Sync android lib to java lib, throw exceptions on errors
2023-02-08 22:07:02 +01:00
Nickolay Shmyrev
d9c6fc4958
Check if ivector folder is required
2023-02-08 21:00:15 +01:00
Nickolay Shmyrev
fff40ce1a1
Gradle doesn't understand + in version
2022-12-18 22:25:26 +01:00
Nicholas Albion
2deb7de1dd
Fixed #883 - use right class loader ( #1228 )
2022-12-17 14:45:15 +03:00
Nicholas Albion
7d87267c31
copied documentation to javadoc ( #1230 )
...
Co-authored-by: Nickolay V. Shmyrev <nshmyrev@gmail.com >
2022-12-17 14:41:33 +03:00
Nicholas Albion
64d84b01b1
added Recognizer.setGrammar(String) for java ( #1229 )
2022-12-17 11:43:27 +03:00
Nickolay Shmyrev
cf2560c9f8
Bump debian requirement
2022-12-14 17:58:40 +01:00
Nickolay Shmyrev
800d3d7089
Bump version
2022-12-14 17:38:53 +01:00
Nickolay Shmyrev
b471207f7a
Protect against segmentation faults with corrupted model folder
2022-12-14 17:32:55 +01:00
Edwin Hendriks
25c59b52e3
add -m (language model) argument to test_microphone.py ( #1219 )
...
* added language model as parameter
* fix fore more help explanation
2022-12-07 22:53:21 +03:00
Nickolay Shmyrev
4c72097478
Allow to configure GPU model path. See https://github.com/alphacep/vosk-server/issues/207
2022-11-19 01:13:42 +01:00
Tomas Mehdi
1053cfa0f8
JSON output_type with texts ( #1180 )
2022-10-26 22:41:04 +03:00
gmat
21a42cb6cd
new output type json for gecko project ( #1166 )
...
add a output type `json` to get output file compatible with transcription file format for the gecko project annotation https://github.com/gong-io/gecko
2022-10-06 16:27:29 +03:00
Nickolay Shmyrev
16c4a0d985
Bump version
2022-09-25 21:00:24 +02:00
Nickolay Shmyrev
298253401a
Update approach to machine detection on cross-compilation
...
See for details issue #1155
2022-09-25 21:00:24 +02:00
Nickolay Shmyrev
32aa980069
Allow to change grammar of existing recognizer. Probably can be faster though
...
if we do not reinit feature pipeline
2022-09-13 23:12:13 +02:00
vadimdddd
7b4d396eb1
fix quotes and import's order ( #1143 )
2022-09-13 21:51:45 +03:00
vadimdddd
36968fbb30
Fix python style issues ( #1140 )
...
* pylint_fix v.2
* init: fix quotes
2022-09-12 23:08:59 +03:00
vadimdddd
7474888801
Fix python style issues ( #1131 )
2022-09-09 00:13:02 +03:00
vadimdddd
d46b7a43eb
Split results by newlines ( #1124 )
2022-08-26 17:22:10 +03:00
vadimdddd
2376b32a8a
Add SRTResult to KaldiRecognizer ( #1080 )
2022-08-24 12:48:18 +03:00
vadimdddd
b8a88cc30c
Add gradio recognizer ( #1114 )
...
Demonstrate speech recognition in gradio
2022-08-19 17:31:47 +03:00
Nickolay V. Shmyrev
be0b117711
Add training colab
2022-08-17 19:11:45 +02:00
Nickolay V. Shmyrev
449c8ea5af
Introduce stop stage espnet style
2022-08-17 14:30:56 +02:00
Nickolay V. Shmyrev
900da76652
Import script locally
2022-08-17 12:50:59 +02:00
Nickolay V. Shmyrev
df0ee24084
Add adaptation colab
2022-08-17 12:38:17 +02:00
Nickolay V. Shmyrev
d3d8f53156
Add Kaldi build colab
2022-08-17 10:02:43 +02:00
vadimdddd
6eee303d7e
Fix decoding files with spaces ( #1084 )
...
Fix decoding files with spaces
2022-08-02 20:56:04 +03:00
Nickolay Shmyrev
053d71f5aa
Bug fix in notebook
2022-08-01 22:59:38 +02:00
Nickolay Shmyrev
4fbbf5882c
Add colab demo
2022-08-01 22:52:57 +02:00
Nickolay Shmyrev
7012103b3b
Simplify the go interface. Move from []byte to strings. Fixes #1095
2022-07-31 09:58:33 +02:00
Nickolay Shmyrev
967024d20a
Fix precedence of current path for dll load. Fixes issue #1096
2022-07-30 09:15:28 +02:00
Nicolas Dato
b966a8078b
Fix comment ( #1091 )
2022-07-26 23:07:25 +03:00
vadimdddd
f63b015284
Add new dependency websockets ( #1079 )
...
add websockets to dependencies
2022-07-19 19:58:24 +03:00
Nickolay Shmyrev
0a9672d910
Attempt to build manylinux wheel
2022-07-15 00:40:38 +02:00
Nickolay Shmyrev
4ccccd0cd2
Bump version
2022-07-14 21:38:36 +02:00
Nickolay Shmyrev
354fb672a3
Merge branch 'master' of github.com:alphacep/vosk-api
2022-07-13 14:09:05 +02:00
Nickolay Shmyrev
73abf0740a
Add Ruby bindings
2022-07-13 14:08:50 +02:00
Nickolay Shmyrev
81c82935ac
Add usage example
2022-07-07 01:09:32 +02:00
Nickolay Shmyrev
ac3ec56584
Add notes about Go and Rust
2022-07-05 01:18:08 +02:00
Nickolay Shmyrev
2cbe12d4d0
Add link to rust bindings
2022-07-05 01:17:43 +02:00
Nickolay Shmyrev
1475b0e986
Async ffmpeg for trancriber and code refactoring
2022-07-05 01:13:05 +02:00
vadimdddd
8ceab0b9b1
Add vosk-server to transcriber ( #1024 )
...
Allow to use vosk-server for transcription
2022-07-04 13:50:38 +03:00
Nickolay Shmyrev
1496b597d3
Fixes issues with models without alignment
2022-07-03 13:00:05 +02:00
vadimdddd
983519e629
Add compatibility with python 3.5 issue( #1021 ) ( #1041 )
...
Added format for python3.5
2022-06-29 18:00:40 +03:00
Nickolay Shmyrev
58fa98ccd7
Wait for microphone to finalize. Fixes crash in issue #1034
2022-06-28 01:01:53 +03:00
Nickolay Shmyrev
a7bc5a22d4
We support Polish now
2022-06-05 23:03:57 +02:00
Rémi Bernon
23bbff0b56
build: Add a CMakeLists.txt. ( #992 )
2022-06-04 17:34:42 +03:00
Kay Gosho
a47b58e2f4
Specify device to get microphone input ( #993 )
2022-06-03 15:33:50 +03:00
Nickolay Shmyrev
8cf64ee93e
Add RISCV support
2022-06-02 01:44:16 +02:00
vadimdddd
630edeb3d6
fixed error if parent directory doesn't exist #988 ( #990 )
...
Create missing parent directory
2022-06-01 17:52:16 +03:00
Nickolay Shmyrev
b1b216d4c8
Bump versions
2022-05-26 15:22:16 +02:00
Nickolay Shmyrev
55dd29b0ff
Fix transcriber bugs while processing folder
2022-05-26 14:05:54 +02:00
Nickolay Shmyrev
ea0568a38d
Change target binary library name and copy header
2022-05-26 13:29:14 +02:00
Nickolay Shmyrev
298c86d0d4
Bump version and add python requirements
2022-05-26 12:46:06 +02:00
Nickolay Shmyrev
859420809b
Add extra comments
2022-05-26 11:45:16 +02:00
Nickolay Shmyrev
0fe3a89768
Update to 0.3.40
2022-05-26 11:41:14 +02:00
Nickolay Shmyrev
5b892fbfc5
Architecture should be universal2
2022-05-25 19:52:05 +03:00
Nickolay Shmyrev
fb4ed21a7f
Shave transcriber code
2022-05-24 22:53:57 +02:00
vadimdddd
4209f3a9fe
Vosk model loader( #871 ) ( #941 )
...
* methods get_model_by_name, get_model_by_lang, get_model were added into the model class
* importing modules changed to using components; introduced constant MODELS_HOME_DIR; simplified code
* added new model folders into init; changed samples and transcriber bin for new mode loader
* changed back in cli.py lang arg to args.lang
* added 3 directories instead of 1 to check for models
* cli.py: added 3 args instead of 1 for model; __init__.py: changed script get_model_path for run get_model_by_name/lang inside current directory
* deleted default env var
* cli.py: changed arg_name; __init__.py: changed const name, changed model loading only for last directory
* deleted unused method
* changed by_name, by_lang methods, added download_model method
* deleted env variable initialization
* deleted print()
* deteled unused modules
* added progress_bar, added folder AppData/Local/vosk for model search
* changed download_model methond; added my_hook method
2022-05-24 21:06:13 +03:00
Nickolay Shmyrev
ff2c80d5f1
Add x86 crossbuild
2022-05-24 20:00:03 +02:00
Nickolay Shmyrev
3a07a08121
Universal binary in node
2022-05-24 17:30:49 +02:00
Nickolay Shmyrev
592da81a8c
Update nuget package for 0.3.38
2022-05-24 17:05:14 +02:00
Nickolay Shmyrev
def8c93711
Remove semicolon
2022-05-24 15:23:03 +03:00
Nickolay Shmyrev
f73088da58
We create universal binary on OSX
2022-05-24 15:11:05 +03:00
Nickolay Shmyrev
06a761ecbd
Bump openblas
2022-05-15 23:58:30 +02:00
Nickolay Shmyrev
97d737a30a
Bump version
2022-05-15 23:36:46 +02:00
Nickolay Shmyrev
c7bffbf603
No need for g++ in C code, fix osx warning
2022-05-15 23:20:33 +02:00
Nickolay Shmyrev
02c40ea612
Bring back incremental decoder, now works better with kaldi fix
2022-05-15 23:20:19 +02:00
Mark Delk
ce5ffb980a
use comma instead of equal sign in rpath linker opts ( #963 )
...
Using `=` for linker options is a GNU extension which doesn't work with
clang.
Using `,` should work for both gcc and clang.
2022-05-12 00:34:43 +03:00
Nickolay Shmyrev
d5ca98a982
Revert incremental decoder patch, leads to very slow decoding in some cases due to lattice blow-up
2022-05-06 00:34:50 +02:00
Nickolay Shmyrev
b0146782d6
Reorganize transcriber binary
2022-04-29 03:01:09 +02:00
Nickolay Shmyrev
5aaea8fc90
Simplify makefile
2022-04-29 02:35:17 +02:00
Chupligin Sergey
5d7752b657
Allow build with shared librares ( #939 )
2022-04-29 03:23:22 +03:00
vadimdddd
9d94746479
Add transcriber tool ( #851 )
...
Add transcriber tool
2022-04-20 14:48:22 +03:00
Nickolay V. Shmyrev
a87f2e1e07
Czech model
2022-04-13 22:31:45 +02:00
Nickolay Shmyrev
7b7d814484
Introduce incremental decoder with confidences in partial results
2022-04-07 01:07:47 +02:00
Nickolay Shmyrev
2daf67f31c
C# style method name
2022-03-29 23:05:27 +02:00
Nickolay V. Shmyrev
62dd631379
Merge pull request #894 from gauthiersornet/patch-1
...
Update VoskDemo.cs
2022-03-22 22:35:16 +03:00
gauthiersornet
2511192ecb
Update VoskDemo.cs
...
To read shorts from a binary buffer => fbuffer[i] = BitConverter.ToInt16(buffer, n);
2022-03-22 20:29:59 +01:00
Nickolay Shmyrev
22cb90de4a
Add Hindi
2022-03-17 20:08:39 +01:00
Nickolay Shmyrev
3951834df2
Move decoding parts to decoding stage. Enable upsampling/downsampling
2022-03-05 14:52:11 +01:00
Nickolay Shmyrev
1ea0de106c
Add trainign setup
2022-03-05 00:28:27 +01:00
Nickolay Shmyrev
a9bf929ebd
Add NLSML output for GPU recognizer
2022-03-03 23:01:49 +01:00
Nickolay Shmyrev
3336cd704b
Add resampler
2022-03-03 21:48:25 +01:00
Nickolay Shmyrev
a57a84f90e
Refactor GPU API to hide the ID and keep it closer to CPU recognizer
2022-03-03 21:09:09 +01:00
Nickolay Shmyrev
ad546a8f1a
Also read processing options
2022-02-17 10:43:05 +01:00
Nickolay Shmyrev
1f447a8dfc
Rename according to Kaldi changes
2022-02-10 20:52:55 +01:00
Nickolay Shmyrev
f574d896e9
Emtpy result should be also xml
2022-02-03 23:43:00 +01:00
Nickolay Shmyrev
a561c2d6d4
Don't add space before string
2022-02-03 23:26:53 +01:00
Nickolay Shmyrev
79b8395be0
Add NLSML output
2022-02-03 23:08:09 +01:00
Nickolay Shmyrev
d2c11a611f
Read list of files from arguments
2022-01-30 22:57:36 +01:00
Nickolay Shmyrev
b0903413b1
Set soname for Android library
2022-01-21 13:22:26 +01:00
Nickolay Shmyrev
2135223490
Put stream information in a single structure
2022-01-12 14:58:43 +01:00
Nickolay Shmyrev
6f86944a06
Implement wave chunking for cuda decoder
2022-01-12 01:32:20 +01:00
Nickolay Shmyrev
9861be2787
Add libs as dependencies in Makefile
2022-01-10 20:21:24 +01:00
Nickolay Shmyrev
c6fab363e6
Don't close channel which not yet started
2022-01-09 15:15:20 +01:00
Nickolay Shmyrev
c32099705f
Fix branch name and add implib dump
2022-01-07 17:33:47 +01:00
Nickolay Shmyrev
a1eac015dc
Add Esperanto
2022-01-07 16:27:57 +01:00
Nickolay Shmyrev
64dfc65d51
Merge branch 'master' of github.com:alphacep/vosk-api
2022-01-05 20:32:25 +01:00
Nickolay Shmyrev
70d5cbd0e0
Update README with Japanese
2022-01-05 20:32:08 +01:00
Nickolay Shmyrev
5428d36d16
Round times
2021-12-26 01:12:18 +01:00
Nickolay V. Shmyrev
ed4c15b7aa
Merge pull request #800 from alphacep/batch
...
Batch GPU decoding
2021-12-24 03:35:51 +03:00
Nickolay Shmyrev
525b722c44
Compile without CUDA too
2021-12-24 01:35:06 +01:00
Nickolay Shmyrev
72bf210164
Put the demo into main folder
2021-12-24 01:07:38 +01:00
Nickolay Shmyrev
93e81c3bc8
Bigger frames per chunk for our big models
2021-12-24 00:22:42 +01:00
Nickolay Shmyrev
cb0f8e6411
Per-stream wait API
2021-12-23 22:34:47 +01:00
Nickolay Shmyrev
848b2dc753
Expose results in Python
2021-12-17 22:57:00 +01:00
Nickolay Shmyrev
60f0396fe0
Reset lattice on endpoint
2021-12-17 01:13:09 +01:00
Nickolay Shmyrev
344e137a61
Decoding works, results are empty yet
2021-12-13 01:21:59 +01:00
Nickolay Shmyrev
6977be7fb7
Batch recognizer draft
2021-12-12 21:37:44 +01:00
Nickolay V. Shmyrev
a4721de8aa
Merge pull request #759 from bertyhell/patch-1
...
Output correct SRT format using milliseconds (NodeJS SRT example)
2021-11-11 12:52:00 +03:00
Bert Verhelst
378ba122c8
Output correct SRT format using miliseconds
2021-11-11 10:49:50 +01:00
Nickolay Shmyrev
287160622f
Update to latest state 0.3.32
2021-11-10 22:26:31 +03:00
Nickolay Shmyrev
a5d788a2e9
One more fix to expose aar dependencies
2021-11-10 00:33:03 +01:00
Nickolay Shmyrev
7f651e1e45
Expose JNA dependency. Fix issue #757
2021-11-09 23:02:17 +01:00
Nickolay Shmyrev
ad5bec114d
Fix issue with empty lattice
2021-11-08 13:46:35 +01:00
Nickolay Shmyrev
f71c62ad0f
Publish Java jars on Mavencentral too
2021-11-07 21:26:33 +01:00
Nickolay Shmyrev
44f7dd2d8b
Publish to sonatype
2021-11-07 20:41:49 +01:00
Nickolay Shmyrev
15a9508a78
Use ndk directory instead of sdk
2021-11-07 14:32:29 +01:00
Nickolay Shmyrev
bdea9a53e8
Bump android version
2021-11-07 14:30:08 +01:00
Nickolay Shmyrev
81f58667ff
Update Android build
2021-11-07 13:45:27 +01:00
Nickolay V. Shmyrev
680a2e4c31
Merge pull request #752 from sskorol/cuda-fix
...
Added missing cuda lib to Vosk compilation flags
2021-11-06 19:04:22 +03:00
sskorol
13993db542
Added missing cuda lib to Vosk compilation flags
2021-11-06 17:24:49 +02:00
Nickolay Shmyrev
59d595a4f0
Replace about in readme
2021-10-31 00:15:52 +02:00
Nickolay Shmyrev
4c562e15a4
Bump version to 0.3.32
2021-10-30 22:45:10 +02:00
Nickolay Shmyrev
5bcdf454ec
Add fbank feature support
2021-10-30 22:45:01 +02:00
Nickolay Shmyrev
4ccdda44ac
Extend documentation
2021-10-12 22:35:31 +02:00
Nickolay Shmyrev
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
Nickolay Shmyrev
fcab5a9581
Revert CFFI bump
2021-10-10 22:09:55 +02:00
Nickolay Shmyrev
e7f5e0ac23
Bump cffi version
2021-10-10 21:21:32 +02:00
Nickolay Shmyrev
9a3906831b
Properly convert lattice. Fixes issue #713
2021-10-08 21:11:00 +02:00
Nickolay Shmyrev
195db43b9e
Rename branches in kaldi repo
2021-10-07 01:18:47 +02:00
Nickolay Shmyrev
332553ec1e
Revert rescoring to more accurate pure fst composition
2021-10-04 01:05:04 +02:00
Nickolay Shmyrev
646af3f652
Explain more about sample rate in constructor
2021-09-17 11:17:38 +02:00
Nickolay V. Shmyrev
f24ac65fcb
Merge pull request #688 from scroot/patch-1
...
Update vosk.go
2021-09-16 18:42:03 +03:00
scroot
14312c93f9
Update vosk.go
...
* fix partial result
+ Free
2021-09-16 09:55:26 +08:00
Nickolay Shmyrev
4346d4155d
Fix go example
2021-09-02 10:48:19 +02:00
Nickolay Shmyrev
7790ac5040
Update versions in bindings
2021-08-31 22:42:42 +02:00
Nickolay Shmyrev
7b3ea0b59d
Merge branch 'master' of github.com:alphacep/vosk-api
2021-08-31 21:56:49 +02:00
Nickolay Shmyrev
e2af710369
Rework rescoring for faster and more accurate results
2021-08-31 21:56:21 +02:00
Nickolay V. Shmyrev
6b1b620f39
Merge pull request #678 from agorman/go-bindings
...
Cleaning up and completing go bindings
2021-08-31 22:34:19 +03:00
Andy Gorman
966524da16
gofmt
2021-08-31 12:24:19 -07:00
Andy Gorman
83c999f298
Cleaning up and completing go bindings
2021-08-31 12:18:34 -07:00
Nickolay Shmyrev
abff8a4f56
Organize makefile structure
2021-07-29 11:58:31 +02:00
Timur
188575f3a2
Added MKL build options ( #647 )
...
Co-authored-by: Kasimov Timur <t.kasimov@cft.ru >
2021-07-29 11:03:39 +03:00
Nickolay Shmyrev
9f4d8ca187
Update doc
2021-07-12 20:29:42 +02:00
Nickolay Shmyrev
72cc8f3a5e
Added test doc
2021-07-12 20:23:49 +02:00
Nickolay Shmyrev
915dcab597
Add doc
2021-07-11 15:54:42 +02:00
Nickolay Shmyrev
d82052b168
Better have it here
2021-07-11 11:26:32 +02:00
Nickolay Shmyrev
dbb65bc71c
Unify example
2021-07-11 11:01:56 +02:00
Nickolay Shmyrev
2498bc595b
Add module file
2021-07-11 10:22:24 +02:00
Nickolay Shmyrev
fee63d712f
Add go bindings
2021-07-10 23:44:15 +02:00
Nickolay Shmyrev
5965ea30e6
Fetch_sub returns original value
2021-07-06 12:11:12 +02:00
Nickolay Shmyrev
5c75495c03
Atomic refcounting for thread safety. See
...
https://github.com/alphacep/vosk-api/issues/606
for more details
2021-07-06 11:09:34 +02:00
Nickolay Shmyrev
98ae3c66cb
Bump version
2021-06-28 02:09:06 +02:00
Nickolay Shmyrev
942e15484a
Protect against multiple resets
2021-06-28 01:59:43 +02:00
Lars Kiesow
2349e66a97
Subtitles require word times ( #607 )
...
This is a port of the recent addition of commit 7ccf743 , adding
`KaldiRecognizer.SetWords(True)` to the other examples dealing with
subtitles to the WebVTT example.
Without this, the example will not work with the most recent `vosk`
(0.3.30) Python package.
2021-06-27 18:06:11 +03:00
Nickolay Shmyrev
5750e3224f
Merge branch 'master' of github.com:alphacep/vosk-api
2021-06-24 20:09:12 +02:00
Nickolay Shmyrev
558b4dd69e
Don't align lattice twice
2021-06-24 20:08:54 +02:00
Lars Kiesow
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
Lars Kiesow
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
Nickolay Shmyrev
7f894f784a
Better check for the model files
2021-06-21 00:19:55 +02:00
Nickolay Shmyrev
a770251151
Bump nodejs version to 0.3.30
2021-06-20 21:30:58 +02:00
Nickolay Shmyrev
7ccf743bb6
SRT requires word times
2021-06-10 10:37:15 +02:00
Nickolay Shmyrev
75bedfe06d
Add a method to show/hide words and their times
2021-06-07 01:04:37 +02:00
Nickolay Shmyrev
4ea9885d44
Bump version
2021-05-30 21:59:46 +02:00
Nickolay Shmyrev
0930def9ec
Fix critical accuracy issues, actually use rescoring
2021-05-30 21:58:06 +02:00
Nickolay Shmyrev
6aa5af7640
Add reset test
2021-05-26 21:22:07 +02:00
Nickolay Shmyrev
e74fe5edf7
Reset reset flag
2021-05-26 21:01:27 +02:00
Nickolay Shmyrev
cbb5d0fcdf
Implement reset method in SpeechService
2021-05-26 20:51:44 +02:00
Nickolay Shmyrev
d489bc40e4
Update Java part too
2021-05-26 00:59:08 +02:00
Nickolay Shmyrev
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
Nickolay Shmyrev
f57b926f66
Unpack library, loading works on Windows
2021-05-23 01:29:29 +02:00
Nickolay Shmyrev
733dca5aea
Attempt to fix loading on Windows
2021-05-22 00:41:30 +02:00
Nickolay Shmyrev
1ab7e8ca87
Use older API for backward compatibility
2021-05-20 20:48:21 +02:00
Nickolay Shmyrev
53426f794c
Add note about Ukrainian
2021-05-20 01:29:15 +02:00
Nickolay Shmyrev
f8189685e5
Add max alternatives output
2021-05-19 18:47:25 +02:00
Nickolay Shmyrev
e6bd200c85
Proper path delimiter on windows
2021-05-13 09:36:56 +02:00
Nickolay Shmyrev
4a4c33fd9d
Load dependent libraries
2021-05-10 01:39:26 +02:00
Nickolay Shmyrev
dc44922b92
Add code to expand path
2021-05-10 01:26:05 +02:00
Nickolay Shmyrev
67896cfba7
Bump bindings versions
2021-05-05 20:50:25 +02:00
Nickolay Shmyrev
ee8663e6d9
RNNLM rescoring support
2021-05-05 19:34:30 +02:00
Nickolay Shmyrev
652c05f052
Reformat and simplify code a bit
2021-05-02 21:44:54 +02:00
Nickolay Shmyrev
193d129d9e
Model can be a symlink
2021-04-30 11:58:11 +02:00
Sadra Sabouri
e995df4bc3
New Examples for Nodejs (Base on Python Examples) ( #515 )
2021-04-30 10:16:36 +03:00
Sergey Korol
f6a30c3626
Added missing GPU methods to nuget package. ( #514 )
2021-04-29 20:57:56 +03:00
Nickolay Shmyrev
ee95420f8f
Fix spk model initialization
2021-04-27 23:24:10 +02:00
Nickolay Shmyrev
2221cd0209
Reorganize methods a bit
2021-04-26 23:25:05 +02:00
Nickolay Shmyrev
8368d831aa
Add async processing demo
2021-04-26 22:34:33 +02:00
Nickolay Shmyrev
91a128b3ed
Fix package name
2021-04-15 13:54:48 +02:00
Nickolay Shmyrev
83d8b63351
Merge branch 'master' of github.com:alphacep/vosk-api
2021-04-15 12:57:17 +02:00
Nickolay Shmyrev
0881aa856f
Update for new API
2021-04-15 12:56:59 +02:00
Nickolay Shmyrev
77abb02ada
Bump version
2021-04-12 12:23:11 +02:00
François Billioud
119c6cd0dc
Update ffi-napi and improve dependency to ref-napi ( #483 )
...
With this change, we will use the same version of ref-napi than the one declared in ffi-napi, which reduce dependency tree, bundle size, risks of errors that could be fixed in one version and not in the other, etc
2021-04-01 22:12:14 +03:00
Nickolay Shmyrev
cc649aa78e
Fixes demo
2021-04-01 20:33:01 +02:00
François Billioud
0b0c9fce0e
Types for typescript projects, and jsDoc ( #461 )
...
Implement Javascript API
2021-04-01 21:25:55 +03:00
Peter Kronenberg
d845e2107f
Allow libvosk.dll to get loaded on Windows ( #478 )
...
* Allow libvosk.dll to get loaded on Windows
Authored-by: Peter Kronenberg <peter.kronenberg@torch.ai >
2021-03-31 18:55:45 +03:00
Nickolay V. Shmyrev
69992a1b39
Android through JNA framework unified with Java ( #476 )
...
* Move to JNA
* Update for android
* Joint publishing
* Fix the developer id
* Added grammar constructor for Java
2021-03-30 23:36:26 +03:00
Nickolay Shmyrev
f351280f49
Allow extra cflags
2021-03-30 19:24:00 +02:00
Nickolay Shmyrev
c15065b044
Wrap short and float
2021-03-30 17:34:00 +02:00
Nickolay Shmyrev
db41f16051
Docs are on the separate project
2021-03-29 00:38:54 +02:00
Nickolay Shmyrev
e276de61be
Give jar a name and fix OSX library path
2021-03-29 00:20:52 +02:00
Nickolay Shmyrev
43c786ab18
Move jars to our own maven and create a demo
2021-03-28 23:38:43 +02:00
Nickolay Shmyrev
1199f39d55
Move project to a library
2021-03-28 13:02:32 +02:00
Nickolay Shmyrev
70aab86257
Remove test code
2021-03-28 10:11:53 +02:00
Nickolay Shmyrev
e4b0af7a8e
Update nuget package, add osx library
2021-03-27 23:40:02 +01:00
Martin Mende
a120d06f6b
Fixed nodejs platform check ( #464 )
2021-03-24 17:08:39 +03:00
Nickolay Shmyrev
e01ca37e45
Add osx module
2021-03-18 00:46:51 +01:00
Nickolay Shmyrev
f5c3d898e2
Option to compile on Mac
2021-03-18 02:10:56 +03:00
Nickolay Shmyrev
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
Nickolay Shmyrev
4be9874ba2
Reformat
2021-02-28 22:40:40 +01:00
Peter Kronenberg
5647a2dc6a
Java example with better type safety, Java objects and support for au… ( #429 )
...
Java example with better type safety, Java objects and support for autoclosable
Authored-by: Peter Kronenberg <peter.kronenberg@torch.ai >
2021-03-01 00:35:31 +03:00
Nickolay Shmyrev
a067a5b5f3
Enable pitch if conf/pitch.conf is present
...
Fixes issue #442
2021-02-26 20:34:17 +01:00
Nickolay Shmyrev
475b0ecfc1
Free symbol table only if we loaded it
2021-02-25 19:17:13 +01:00
Nickolay V. Shmyrev
2a9a605144
Merge pull request #436 from sskorol/435-sync-master-with-gpu
...
Sync master with GPU
2021-02-22 13:41:37 +03:00
sskorol
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
Nickolay Shmyrev
11c16610ee
Fix memory leaks for big models. Fixes issue #425 .
2021-02-19 19:25:07 +01:00
Nickolay Shmyrev
2f4124eb66
Demonstrate speaker
2021-02-16 17:40:21 +01:00
Nickolay Shmyrev
db3e31d7ce
Automatically put .so file in resources
2021-02-16 17:33:09 +01:00
Nickolay Shmyrev
d917af21ab
Better search for Windows dlls
2021-02-12 22:24:54 +01:00
Nickolay Shmyrev
948c8c7cfd
Update to 0.3.21
2021-02-12 10:13:50 +01:00
Nickolay Shmyrev
dec8e1acf3
Move to JNA instead of JNR-FFI for better Android compatibility
2021-02-11 00:04:19 +01:00
Nickolay Shmyrev
3c020526ce
No need for byte buffer
2021-02-10 23:32:47 +01:00
Nickolay Shmyrev
b0da19b07f
Java API through JNR-FFI
2021-02-10 23:16:20 +01:00
Nickolay Shmyrev
70bcd9b018
Platform is hardcoded now
2021-02-09 23:43:56 +01:00
Nickolay Shmyrev
d2604b609d
Copy out lib files too
2021-02-09 23:36:32 +01:00
Nickolay Shmyrev
e960e0cacf
Proper libraries and demo
2021-02-09 21:43:21 +01:00
Nickolay Shmyrev
77b114d434
Rework node bindings to use node-ffi-napi
2021-02-08 23:00:56 +01:00
Nickolay V. Shmyrev
2860092cef
Merge pull request #401 from proger/patch-1
...
test_microphone: AcceptWaveform wants bytes
2021-02-08 01:50:07 +03:00
Vlad Ki
c6119c4835
test_microphone: AcceptWavform wants bytes
2021-02-08 00:38:28 +02:00
Nickolay Shmyrev
415d1927e0
Add win32 wheel
2021-02-07 23:08:27 +01:00
Nickolay Shmyrev
3d1e21d242
Update dockcross build to cffi
2021-02-07 21:33:39 +01:00
Nickolay Shmyrev
7a75e1c3f4
Add arm architectures
2021-02-07 20:28:14 +01:00
Nickolay Shmyrev
c3430e448a
Add build for Windows wheel
2021-02-07 18:11:38 +01:00
Nickolay Shmyrev
ae49ea60d2
Rework manylinux to use cffi
2021-02-07 15:26:23 +01:00
Nickolay Shmyrev
02dc0ce0c8
Take source location from environment
2021-02-07 15:17:35 +01:00
Nickolay Shmyrev
15697a18e8
Platform-specific wheel
2021-02-07 14:58:10 +01:00
Nickolay Shmyrev
481881e59d
Fully move python to cffi
2021-02-07 13:23:03 +01:00
Nickolay Shmyrev
11a25b26a7
Add cffi wrapper
2021-02-07 10:57:57 +01:00
Nickolay Shmyrev
bf87358f6c
Add win32 build
2021-02-07 10:12:32 +01:00
Nickolay Shmyrev
04a8242230
Add vosk-api build
2021-02-07 01:55:47 +01:00
Nickolay Shmyrev
ceb96c301c
Separate openfst root
2021-02-07 01:48:45 +01:00
Nickolay Shmyrev
307df8fdc0
Add Win cross-compilation docker
2021-02-07 01:41:37 +01:00
Nickolay Shmyrev
c44875a2dd
Build libvosk in src folder, will be used for many bindings
2021-02-07 00:42:25 +01:00
Nickolay Shmyrev
31f11990ca
Rename voskrecognizer
2021-02-07 00:32:47 +01:00
Nickolay Shmyrev
b79b85856d
Refactor C# API to properly work with nuget and precompiled libvosk.so library
2021-02-06 23:10:51 +01:00
Nickolay Shmyrev
6e861c6a19
Add nuget platforms
2021-02-05 00:39:27 +01:00
Nickolay Shmyrev
cf62296a51
Update flags to hopefully fix the build
2021-02-02 14:43:12 +01:00
Nickolay Shmyrev
387b132814
Fix model version in Makefile. Thanks to Peter Kronenberg.
2021-01-26 23:19:34 +01:00
Nickolay Shmyrev
de83de8624
Implement decoding on iOS with a microphone
2021-01-24 21:59:21 +01:00
Nickolay Shmyrev
fe91b5a717
Preprocess header on the fly
2021-01-10 21:11:35 +01:00
Nickolay Shmyrev
a052506a5d
Add cffi example
2021-01-10 20:53:43 +01:00
Nickolay Shmyrev
6f2d6d0d69
Proper microphone recognizer with the queue
2021-01-09 23:16:35 +01:00
Nickolay Shmyrev
a8ae6025bd
Add a bit more optimization
2021-01-09 16:16:32 +01:00
Nickolay Shmyrev
1b8332a609
Raise to 0.3.17
2021-01-09 02:29:56 +01:00
Nickolay Shmyrev
fe16ec7e57
Set lowest arch for linux
2021-01-09 01:47:23 +01:00
Nickolay Shmyrev
c5ce5e46bd
Add c++17
2021-01-09 01:46:13 +01:00
Nickolay Shmyrev
99d66670bc
Update Android build
2021-01-08 13:30:28 +01:00
Nickolay Shmyrev
072b42cac6
Use our own dockcross
2021-01-08 00:56:18 +01:00
Nickolay Shmyrev
acadb5b4c2
Add optimization
2021-01-07 23:41:13 +01:00
Nickolay Shmyrev
2e1de6c3af
No need for python 3.5 anymore
2021-01-07 23:20:54 +01:00
Nickolay Shmyrev
67de30908b
Use openblas_clapack
2021-01-07 22:37:56 +01:00
Nickolay Shmyrev
9d398eff0e
Remove armv6, too slow anyway. Build with new dockcross.
2021-01-06 16:26:23 +01:00
Nickolay Shmyrev
02b7312a00
Build with openblas-clapack to avoid fortran
2021-01-06 01:11:03 +01:00
Nickolay Shmyrev
08c35e84f3
Update demo with spk vector check
2020-12-23 22:21:12 +01:00
Nickolay Shmyrev
b92a5c1fc7
Update wheels to openfst 1.8.0
2020-12-22 23:27:01 +01:00
Nickolay Shmyrev
8997a587c5
Fix warnings in preparation for openfst 1.8.0
2020-12-22 21:16:20 +01:00
Nickolay Shmyrev
dc3d03d742
Make sure we have result field in json
2020-11-29 19:19:50 +01:00
Nickolay Shmyrev
84df40715c
Add Filipino
2020-11-19 14:53:46 +01:00
Nickolay Shmyrev
b639fb501a
Package US model on bintray
2020-11-04 22:08:03 +01:00
Nickolay Shmyrev
746ff47757
Split long lines in subtitles
2020-11-03 15:13:16 +01:00
Nickolay Shmyrev
2d62db8118
Update link in readme
2020-10-31 10:03:25 +01:00
Nickolay Shmyrev
7a2adcd9ba
Add nuget wraps
2020-10-26 15:57:40 +01:00
Nickolay Shmyrev
9ccf3ef0e8
Introduce CMVN in feature pipeline
2020-10-22 23:56:36 +02:00
Nickolay V. Shmyrev
0edab6d558
Merge pull request #259 from ThThoma/add-valid-word-check
...
add isWordRecognizable()
2020-10-22 15:53:04 +03:00
Athanasios Thoma
4b344f0cd8
rename
2020-10-22 14:09:50 +03:00
Athanasios Thoma
17ddc4d5ba
add isWordRecognizable()
2020-10-21 10:00:39 +03:00
Nickolay Shmyrev
3e33860c47
Update to latest 0.3.15 changes
2020-10-20 23:50:39 +03:00
Nickolay Shmyrev
0269a10833
Critical ivector bugfix and version 0.3.15
2020-10-13 01:28:46 +02:00
Nickolay Shmyrev
7af3e9a334
Add srt example
2020-10-07 13:43:09 +02:00
Nickolay Shmyrev
d666876be1
Revert compile flags
2020-10-05 01:24:32 +02:00
Nickolay Shmyrev
564fab7ec1
Update documentation
2020-10-05 00:16:15 +02:00
Nickolay Shmyrev
155c6c2a2a
Don't crash with grammar and static graphs
2020-10-05 00:13:25 +02:00
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
8d88b89db1
Fix reserved identifier violation. Closes issue #226
...
Thanks to Markus Elfring
2020-09-23 21:16:34 +02:00
Nickolay Shmyrev
62885e8963
Update descriptions
2020-09-22 11:30:27 +02:00
qo6xup6
9fc094a5da
Update kaldi_recognizer.h
2020-09-22 10:11:29 +08:00
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
9696f4c917
Mention Dutch
2020-09-18 17:31:17 +02:00
Nickolay Shmyrev
55abf5f5ac
Dynamic arch in pip module
2020-09-13 22:08:36 +02:00
Nickolay Shmyrev
a1b2e41710
Mention we support Indian English
2020-09-09 23:28:55 +02:00
Nickolay Shmyrev
dff4ab26e4
Library is now vosk_jni
2020-09-01 18:27:54 +02:00
Nickolay Shmyrev
83b6e1cdf7
Speech service for more flexible recognizer initialization
...
Publish repo on jcenter
2020-09-01 16:32:15 +02:00
Nickolay Shmyrev
38dbaa15ea
Load JNI inside library itself
2020-09-01 12:44:44 +02:00
Nickolay Shmyrev
0e531b6061
Organize Makefile
2020-08-23 20:10:48 +02:00
Nickolay Shmyrev
de94ef5537
Add speaker C demo
2020-08-14 11:33:41 +02:00
Nickolay Shmyrev
6ef9d13877
Add Italian
2020-08-03 01:31:30 +02:00
Nickolay Shmyrev
1c7b94757d
Don't attempt to resize to empty matrix
2020-07-31 16:45:05 +02:00
Nickolay Shmyrev
83486e0bef
Spk vector fix
2020-07-31 12:58:23 +02:00
Nickolay Shmyrev
9787e8a53f
No .html in links
2020-07-21 10:15:27 +02:00
Nickolay Shmyrev
f59d6685ad
Fix confidences
2020-07-15 10:24:08 +02:00
Nickolay Shmyrev
8a986ef384
Require KALDI_MKL to be 1
2020-07-12 11:03:22 +02:00
Nickolay Shmyrev
78f9f55e14
Fixes description
2020-07-12 10:37:56 +02:00
Nickolay Shmyrev
c2e006f664
Some probably helpful flags for npm on osx
2020-07-11 20:54:13 +02:00
Nickolay V. Shmyrev
4b8e9737a5
Update README.md
2020-07-08 01:38:03 +02:00
Nickolay Shmyrev
722b09eaa4
Ignore words missing in the vocabulary
2020-07-08 01:35:50 +02:00
Nickolay Shmyrev
f5b4f5a1f2
Added C test
2020-07-08 01:35:50 +02:00
Nickolay Shmyrev
4407d8da55
Another timestamp bugfix
2020-07-08 01:35:50 +02:00
Nickolay Shmyrev
73b73527cd
Release memory when final result is received to reduce memory pressure.
2020-07-08 01:35:50 +02:00
Nickolay Shmyrev
4df0e3a741
Actually show the distance
2020-07-08 01:35:49 +02:00
He1nr1chK
1a771e0172
Added cosine distance function
2020-06-23 20:10:14 +02:00
Nickolay Shmyrev
4333c3c242
Build dockcross with python 3.8
2020-06-23 01:11:07 +02:00
Nickolay V. Shmyrev
b831c9ad57
Merge pull request #151 from hviana/patch-1
...
Add support for speaker model in Android
2020-06-23 00:07:26 +03:00
Nickolay Shmyrev
e5c08f7710
Allow to continue after final result. See for discussion
...
https://github.com/alphacep/vosk-api/issues/146
2020-06-22 23:04:09 +02:00
Henrique Emanoel Viana
51c2968595
fix
2020-06-22 18:01:42 -03:00
Henrique Emanoel Viana
5993376322
Add suport to SpkModel
2020-06-22 17:51:55 -03:00
Nickolay Shmyrev
c4281622b9
Added node speaker demo
2020-06-22 21:45:50 +02:00
Nickolay Shmyrev
9d26014de2
Use wider beams by default to avoid accuracy confusion
2020-06-19 16:10:30 +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
6bd102d778
Fixes timing issue #125
2020-06-15 02:04:02 +02:00
Nickolay Shmyrev
d3d6af5712
Define os in a single place
2020-06-12 10:35:58 +02:00
Nickolay V. Shmyrev
876093446f
Merge pull request #127 from nnkalita/master
...
added android build support on macOS
2020-06-12 11:32:27 +03:00
Nickolay Shmyrev
336f219f09
No Qr code for wechat anymore
2020-06-11 12:57:32 +02:00
Nickolay Shmyrev
584251cbdc
Remove chinese-only
2020-06-11 09:18:34 +02:00
Nickolay Shmyrev
a34995a788
Process audio in chunks for imporved accuracy
2020-06-11 01:06:11 +02:00
Nickolay Shmyrev
998e5da227
Update rules for joining wechat
2020-06-10 15:07:10 +02:00
Nickolay Shmyrev
e04c15e367
Fix
2020-06-06 11:15:23 +02:00
Nickolay Shmyrev
b81f69d407
Avoid overflow. See issue #128
2020-06-06 10:43:44 +02:00
Nickolay Shmyrev
0ac2064281
Few more words
2020-06-06 10:07:12 +02:00
Nickolay Shmyrev
1d00bd244e
Multithreaded testing
2020-06-06 00:40:15 +02:00
Nickolay Shmyrev
8f5efc58c9
Disable ivector pipeline without ivectors
2020-06-05 19:34:04 +02:00
Nayan Kalita
a0c5ae1b5e
Update build-kaldi.sh
...
added android build from mac.
2020-06-05 20:10:28 +05:30
Nayan Kalita
99f48f9de1
Merge remote-tracking branch 'upstream/master'
2020-06-05 19:15:42 +05:30
Nayan Kalita
1948b23f32
Update build-kaldi.sh
...
Updated based feedback.
2020-06-05 18:03:01 +05:30
Nickolay Shmyrev
c9eb572fc5
Move documentation to our website
2020-06-05 01:31:13 +02:00
Nickolay Shmyrev
7d9895ff81
Add API documentation in the header
2020-06-04 22:47:54 +02:00
Nickolay Shmyrev
d507210ef8
Add npmignore and pure javascript package
2020-06-03 17:47:15 +02:00
Nickolay Shmyrev
db0a3d23d5
Add repackages librispeech model
2020-06-03 17:24:28 +02:00
Nickolay Shmyrev
f4f920f3cd
Proper cross-compilation with setuptools
2020-06-02 00:36:16 +02:00
Nickolay Shmyrev
75993ea276
Update to 0.3.8
2020-06-01 00:55:28 +02:00
Nickolay Shmyrev
ee9bacb092
Reset pipeline to save memory
2020-06-01 00:54:47 +02:00
Nickolay Shmyrev
b1e775c67b
Better speaker identification without silence frames
2020-05-31 23:46:42 +02:00
Nickolay Shmyrev
d631e567aa
Add README
2020-05-31 02:21:07 +02:00
Nickolay Shmyrev
9edf45be42
Sync version
2020-05-31 02:08:35 +02:00
Nickolay Shmyrev
8b4b3c646a
Nodejs support
2020-05-31 02:07:01 +02:00
Nickolay Shmyrev
31bb0557d9
Add mkl support
2020-05-30 23:22:14 +02:00
Nickolay Shmyrev
4593183cf9
Create gen if doens't exist. Thanks to BMI24.
2020-05-25 00:32:42 +02:00
Nickolay Shmyrev
fdc45f1187
Better link on wechat
2020-05-23 21:13:23 +02:00
Nickolay Shmyrev
b3d3c6d12c
Fix mistake, thanks to Shaheen
2020-05-23 01:12:31 +02:00
Nickolay Shmyrev
f5f0794def
Add logo
2020-05-22 15:24:57 +02:00
Nickolay Shmyrev
55664fcca0
Add wechat group
2020-05-22 09:56:54 +02:00
Nickolay Shmyrev
afbf330f16
Make ivector extractor optional
2020-05-18 23:56:42 +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
78025435e4
Windows is fully supported now
2020-05-09 09:18:10 +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
b12914955c
Add x86 build
2020-05-08 11:33:25 +02:00
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 V. Shmyrev
944dc87531
Update readme to mention aarch64
2020-05-05 00:55:29 +02:00
Nickolay Shmyrev
5c4dd4644e
Update version
2020-05-03 20:52:43 +02:00
Nickolay Shmyrev
9bbd172cfd
Some more links
2020-05-02 01:37:10 +02:00
Nickolay Shmyrev
dbf9de77c3
Document model training and model structure
2020-05-02 01:11:25 +02:00
Nickolay Shmyrev
8b790cd162
Better android logging
2020-05-01 20:02:46 +02:00
Nickolay Shmyrev
80219066e9
Expose verbose level in the API
2020-05-01 19:02:57 +02:00
Nickolay Shmyrev
26fa5f098f
Updated link to English model
2020-04-30 15:19:13 +02:00
Nickolay Shmyrev
d75bb36131
Fix model download path
2020-04-30 11:04:35 +02:00
Nickolay Shmyrev
30c5e8ca79
Link to lm library for rescoring
2020-04-30 10:52:15 +02:00
Nickolay Shmyrev
c00e36fab6
Rearrange models
2020-04-30 10:47:10 +02:00
Nickolay Shmyrev
80e60b9118
LM Rescoring
2020-04-28 22:17:34 +02:00
Nickolay Shmyrev
e3a95a44bc
Added Turkish model
2020-04-28 10:10:35 +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
e09f32b4b4
Properly stop listening so it can continue later
2020-04-27 09:00:32 +02:00
Nickolay Shmyrev
3803ab345d
Proper reference couting of the models to avoid memory issus
2020-04-23 23:37:52 +02:00
Nickolay V. Shmyrev
889b43136f
Update README.zh.md
2020-04-23 12:43:00 +02:00
John Baber-Lucero
b517cf46af
Fix some grammar/punctuation
2020-04-23 00:28:34 -04:00
Nickolay Shmyrev
ffd810fe00
Fix threading bug
2020-04-22 22:15:45 +02:00
Nickolay V. Shmyrev
a1a0ed70a1
Update README.zh.md
2020-04-22 18:29:01 +03:00
Nickolay Shmyrev
1554d9ede7
Added per-language readme
2020-04-22 13:21:36 +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
3caaa32ec0
How to ask for the accuracy updates
2020-04-20 23:11:52 +02:00
Nickolay Shmyrev
3facf3ccf5
UI updates
2020-04-20 11:08:18 +03:00
Nickolay Shmyrev
fad954e6e3
Full iOS project
2020-04-19 22:48:47 +03:00
Nickolay Shmyrev
c4809cb618
Added Vietnamese model
2020-04-19 20:14:05 +02:00
Nickolay Shmyrev
a241423baf
Added iOS bits
2020-04-18 17:34:03 +03:00
Nickolay Shmyrev
1e9421dd38
Add a note about iOS
2020-04-18 15:41:51 +02:00
Nickolay Shmyrev
b09ffda760
Fixes links and issue #59
2020-04-11 22:15:46 +02:00
Nickolay Shmyrev
aeff663a7c
Fix pocketsphinx references in Android sources
2020-04-09 21:50:38 +02:00
Nickolay Shmyrev
fcd17fcd4c
Added Russian model 0.9
2020-04-07 17:48:29 +02:00
Nickolay Shmyrev
feffb2711d
Repair travis build
2020-04-04 20:49:06 +02:00
Nickolay Shmyrev
f76e5b592f
kaldi-ru-0.8
2020-04-04 10:27:02 +02:00
Nickolay Shmyrev
71bdc900e3
C-only wrapper
2020-04-04 10:22:01 +02:00
Nickolay Shmyrev
96bbf5abc2
Add C API
2020-04-04 10:04:49 +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
Nickolay Shmyrev
3310acaf54
Add lm to kaldi-android
2020-03-28 22:45:38 +01:00
Nickolay V. Shmyrev
e8722d462d
Merge pull request #54 from andremendesc/master
...
Fixes folder name instruction for python model on microphone test
2020-03-25 08:37:25 +03:00
André Mendes
14b2c13ed6
Fixes folder name instruction for python model on microphone test
2020-03-25 01:01:23 -03:00
Nickolay Shmyrev
19af324096
Small fix by Funny Jingl
2020-03-19 23:24:41 +01:00
Nickolay Shmyrev
0ca7b94e08
Add link on kaldi-ru-0.7
2020-03-19 20:14:41 +01:00
Nickolay Shmyrev
04ed310229
Move models list to doc
2020-03-15 22:39:57 +01:00
Nickolay Shmyrev
7ac33d521c
Added information about models
2020-03-15 22:27:47 +01:00
Nickolay V. Shmyrev
08ada63da4
Added note about other projects
2020-03-15 02:48:49 +03:00
Nickolay Shmyrev
cef3fd72fb
Disable NEON fpu on ARMv6
...
Fixes issue #46
2020-03-10 00:24:57 +01:00
Nayan Kalita
bca0b86e37
android build support on macOS
2020-03-06 20:57:56 +05:30
Nickolay V. Shmyrev
bf973ff434
Merge pull request #43 from camillem/patch-1
...
Typo in folder name
2020-03-02 15:47:25 +03:00
camillem
a172d60b20
Typo in folder name
2020-03-02 13:46:34 +01:00
Nickolay Shmyrev
060e4395c2
Fix repeating results issue #42
...
Thanks to Yondu Tsai
2020-03-02 13:41:27 +01:00
Nickolay Shmyrev
03f1417454
Added small readme
2020-03-01 09:12:09 +01:00
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 V. Shmyrev
5ba9e353c7
Added contacts
2020-02-25 02:44:28 +03:00
Nickolay V. Shmyrev
be117bfbb8
Update README.md
2020-02-25 02:39:14 +03:00
Nickolay V. Shmyrev
c4f9bfe735
Update README.md
2020-02-24 17:50:39 +03:00
Nickolay Shmyrev
cc96ef700f
Fix mistake
2020-02-24 01:25:29 +01:00
Nickolay Shmyrev
cb41d8c94b
Added C# test
2020-02-24 00:25:15 +01:00
Nickolay Shmyrev
8913b93703
Fix message
2020-02-23 16:05:34 +00:00
Nickolay Shmyrev
174bf7b0ff
Minor fixes
2020-02-23 15:06:06 +01:00
Nickolay Shmyrev
7e44844cd5
Added dockcross images for arm builds
2020-02-23 10:19:31 +01:00
Nickolay Shmyrev
c0aa87af1b
Build speaker model too
2020-02-21 09:53:00 +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
bd4a48d5a8
Added spkid to java
2020-02-16 17:12:54 +01:00
Nickolay Shmyrev
aa91ccf68b
Added speaker identification
2020-02-16 17:04:37 +01:00
Nickolay Shmyrev
bda43565e1
Added the doc about langauge model recompilation with opengrm
2020-02-10 20:39:59 +01:00
Nickolay Shmyrev
8c9bae3ad1
Update version for Kaldi rebuild
2020-02-08 23:40:42 +01:00
Nickolay V. Shmyrev
87fc3bc073
Make structure more clear
2020-02-02 23:10:35 +03:00
Nickolay Shmyrev
9c101ffa86
Strip binary on release
...
Fixes issue #12 .
2020-01-29 22:22:26 +01:00
Nickolay V. Shmyrev
5649d9e3c7
Merge pull request #22 from dtreskunov/issue-19
...
translate exceptions from C++ to Python
2020-01-29 23:12:41 +03:00
Denis Treskunov
5ee96b6d04
translate exceptions from C++ to Python
...
Wrap each API call in a try/catch.
See http://www.swig.org/Doc4.0/Python.html#Python_nn44
2020-01-28 14:12:53 -08:00
Nickolay V. Shmyrev
6a7854919e
Clarify Pip install is sufficient.
2020-01-27 12:33:27 +03:00
Nickolay Shmyrev
a6f6c0409b
Demonstrate grammar compilation on the fly
2020-01-22 23:31:21 +01:00
Nickolay Shmyrev
41446c980c
Use json library for convenience
2020-01-22 22:37:03 +01:00
Nickolay Shmyrev
7bed44a96e
Automatically download model
2020-01-19 22:07:47 +01:00
Nickolay Shmyrev
3f7bd2f586
Added java example
2020-01-19 21:57:08 +01:00
Nickolay Shmyrev
2ba8466e0a
Avoid hardcoded folders, fixes issue #14 . Thanks to Bill Lambert.
2020-01-19 20:30:18 +01:00
Nickolay Shmyrev
f80dcce5ed
Clarify licences
2020-01-19 19:33:55 +01:00
Nickolay Shmyrev
f4aed3e9a4
Added note about runnign the code
2020-01-18 00:28:35 +01:00
Nickolay Shmyrev
5c4ef66a08
Update README
2020-01-18 00:20:19 +01:00
Nickolay Shmyrev
29d2564efd
Let it be 3.4
2020-01-12 13:16:59 +01:00
Nickolay Shmyrev
380fa9c7c8
Added a warning to download the model
2020-01-11 20:24:34 +01:00
Nickolay Shmyrev
e55c6e09f8
Simplify swig task
2020-01-11 08:14:32 +01:00
Nickolay Shmyrev
355b58447a
No need to link with python library
2020-01-10 19:57:41 +00:00
Nickolay Shmyrev
fe35675eaa
Added basic travis
2020-01-10 20:01:48 +01:00
Nickolay Shmyrev
ae9db8652a
Update gradle plugin to properly report about missing local properties.
...
Fix issue #8
2020-01-03 20:24:47 +01:00
Nickolay Shmyrev
ac3e52596c
Remove premature exit
2020-01-03 20:20:51 +01:00
Nickolay V. Shmyrev
17bffb6739
Update README.md
2020-01-03 09:58:08 +03:00
Nickolay V. Shmyrev
8839771794
Update README.md
2020-01-03 02:06:28 +03:00
Nickolay V. Shmyrev
95ee23521b
Update README.md
2020-01-03 01:35:57 +03:00
Nickolay Shmyrev
38672ad1ca
Update to current state
2020-01-02 21:53:07 +01:00
Nickolay Shmyrev
79cee1cab6
Update to use shared sources
2020-01-02 21:51:25 +01:00
Nickolay Shmyrev
3aece57b6e
Kaldi doesn't use logarc
2020-01-02 20:48:08 +01:00
Nickolay Shmyrev
78e66149f8
Imported Python bindings and Node bindings
2020-01-02 20:46:14 +01:00
Nickolay Shmyrev
6805077934
Moved android things to a folder in preparation for merge with python bindings
2020-01-02 20:41:39 +01:00
Nickolay Shmyrev
688178ba5f
-O3 implies tree vectorization
2020-01-02 19:59:17 +01:00
Nickolay Shmyrev
cc13917903
Reuse symbol table from the grammar instead of separate file.
2019-12-25 23:54:53 +01:00
Nickolay Shmyrev
65ebfb0dac
Update for disambig in lookahead
2019-11-25 23:29:05 +01:00
Nickolay Shmyrev
3954d89329
Use Atom architecture for emulator instead of SandyBridge
2019-11-13 20:45:05 +01:00
Nickolay Shmyrev
41ebb41bd8
Add x86 plugin
2019-11-12 00:05:15 +01:00
Nickolay Shmyrev
545800454b
Update for arm64
2019-11-03 00:20:03 +01:00
Nickolay V. Shmyrev
edad7eba9e
Added link to XNNPack
2019-10-09 14:59:40 +03:00
Nickolay Shmyrev
bb8188afe6
More compact ngram fsts
2019-09-23 01:38:43 +02:00
Nickolay Shmyrev
305961e8dc
Update for lookahead model
2019-09-20 22:39:39 +02:00
Nickolay Shmyrev
06972ec3ad
Simplify AcceptWaveform API
2019-09-11 18:55:24 +02:00
Nickolay Shmyrev
345dfde6fb
Optimization for speed test
2019-09-10 21:50:18 +02:00
Nickolay Shmyrev
1326d3820f
Unified build script without docker
2019-09-09 18:19:30 +02:00
Nickolay Shmyrev
9437f88ce2
Add readme
2019-09-05 13:00:23 +02:00
Nickolay Shmyrev
67b5814108
Allow model path specification
2019-09-05 12:59:23 +02:00
Nickolay Shmyrev
5a49c26d9d
Initial import
2019-09-03 19:45:19 +02:00