Commit Graph

51 Commits

Author SHA1 Message Date
Roy Shilkrot
73c91765a5 refactor: Update whisper model path and add flag for model loaded status 2024-07-19 20:59:55 -04:00
Roy Shilkrot
b3e4bfa33a
refactor: Enable partial transcription with a latency of 1000ms (#141)
* refactor: Enable partial transcription with a latency of 1000ms

* refactor: Update CMakePresets.json and buildspec.json

- Remove the "QT_VERSION" variable from CMakePresets.json for all platforms
- Update the "version" of "obs-studio" and "prebuilt" dependencies in buildspec.json
- Update the "version" of "qt6" dependency in buildspec.json
- Update the "version" of the project to "0.3.3" in buildspec.json
- Update the "version" of the project to "0.3.3" in CMakePresets.json
- Remove unused code in whisper-processing.cpp

* refactor: Add -Wno-error=deprecated-declarations option to compilerconfig.cmake

* refactor: Update language codes in translation module
2024-07-19 14:02:24 -04:00
Roy Shilkrot
9ecd759968
refactor: Update whispercpp dependency to version 0.0.3 (#103) 2024-05-30 23:00:04 -04:00
Roy Shilkrot
5227a437b6
VAD based segmentation (#97)
* refactor: Add whisper_buffer to transcription_filter_data struct

* refactor: Add sentence_psum_accept_thresh to transcription_filter_data struct

* refactor: Update buffer size and overlap size in whisper-processing.cpp

* refactor: Update buffer size and overlap size in whisper-processing.cpp

* refactor: Add audio-file-utils.cpp for audio file handling

* refactor: Update buffer size and overlap size in whisper-processing.cpp

* refactor: Add external model option to translation settings

* refactor: Add support for input tokenization style in translation settings

* refactor: Update buffer size and overlap size in whisper-processing.cpp
2024-05-16 15:07:00 -04:00
Roy Shilkrot
31c41a9574
Offline transcription accuracy tests (#96)
* Update translation-utils.h, transcription-filter.h, whisper-model-utils.h, model-find-utils.h, and model-downloader.h

* Update create_context function to include ct2ModelFolder parameter

* fix: add fix_utf8 flag to transcription_filter_data struct

* Update create_context function to include ct2ModelFolder parameter

* Update read_text_from_file function to include join_sentences parameter

* fix: Update VadIterator::reset_states to include reset_hc parameter

* Update create_context function to include whisper_sampling_method parameter

* Update tests README with additional configuration options

* feat: Add function to find file in folder by regex expression

* refactor: Improve text conditioning logic in transcription-filter.cpp

* refactor: Improve text conditioning logic in transcription-filter.cpp

* chore: Update ctranslate2 dependency to version 1.2.0

* refactor: Improve text conditioning logic in transcription-filter.cpp

* chore: Update cmake BuildCTranslate2.cmake to disable -Wno-comma warning

* refactor: Update translation context in whisper-processing.cpp and translation-utils.cpp
2024-05-10 17:37:09 -04:00
Roy Shilkrot
493ecad254
Update CTranslate2 and cpu_features dependencies (#94)
* Update CTranslate2 and cpu_features dependencies

* Update CTranslate2 and cpu_features dependencies

* Update dependencies and fix special tokens handling

* Add BUILD_BYPRODUCTS to CMake build command

* Update version to 0.2.5 in buildspec.json
2024-04-30 09:48:23 -04:00
Roy Shilkrot
ab1b74a35c
Overlap analysis (#92)
* Update buffer size and overlap size in whisper-processing.h and default buffer size in msec in transcription-filter.cpp

* Update buffer size and overlap size in whisper-processing.h and default buffer size in msec in transcription-filter.cpp

* Update suppress_sentences in en-US.ini and transcription-filter-data.h

* Update suppress_sentences and fix whitespace in transcription-filter-data.h, whisper-processing.h, transcription-utils.cpp, and transcription-filter.h

* Update whisper-processing.cpp and whisper-utils.cpp files

* Update findStartOfOverlap function signature to use int instead of size_t

* Update Whispercpp_Build_GIT_TAG to use commit 7395c70a748753e3800b63e3422a2b558a097c80 in BuildWhispercpp.cmake

* Update buffer size and overlap size in whisper-processing.h and default buffer size in msec in transcription-filter.cpp

* Update unused parameter in transcription-filter-properties function

* Update log level and add suppress_sentences feature in transcription-filter.cpp and whisper-processing.cpp

* Add translation output feature in en-US.ini and transcription-filter-data.h

* Add DTW token timestamps and buffered output feature

* trigger rebuild

* Refactor remove_leading_trailing_nonalpha function to improve readability and performance

* Refactor is_lead_byte and is_trail_byte macros for improved readability and maintainability

* Refactor is_lead_byte and is_trail_byte macros for improved readability and maintainability

* trigger build
2024-04-25 17:14:13 -04:00
Roy Shilkrot
65da380f9f
Bump whisper, clblast, add buffered output (#90)
* Bump whisper, clblast, add buffered output

* Update CPU_OR_CUDA environment variable error messages

* Update Cublas validation in Package-Windows.ps1 and initialize function in captions-thread.h

* Update Cublas validation and fix typo in Package-Windows.ps1

* Update default whisper model path to Whisper Tiny English (74Mb)

* Update translation strings for multiple locales
2024-04-18 10:28:32 -04:00
Kaito Udagawa
e5a10f48cc
Fix add_custom_command to accept the argument with paren (#88)
* Update FetchOnnxruntime.cmake

* Update FetchOnnxruntime.cmake
2024-04-15 21:38:46 -04:00
Kaito Udagawa
f4307168de
Update build scripts according to the latest obs-plugintemplate (#87)
* Update build-project.yaml

* Update action.yaml

* Update helpers_common.cmake

* Update compilerconfig.cmake

* Update .clang-format

* Fix

* Fix

* Update build-project.yaml

* Update check-format.yaml

* Update push.yaml

* Update build-project.yaml
2024-04-15 08:19:40 -04:00
Roy Shilkrot
f79571f316
Add Silero VAD (#85)
* Add Silero VAD model and integrate it into the transcription filter

* Fix Silero VAD model path and enable n_threads

* Update translation strings for multiple locales

* Update Onnxruntime library linking and fix compiler warning

* Fix variable naming and type casting in Silero VAD implementation

* Update Silero VAD model path and enable n_threads
2024-04-13 22:39:28 -04:00
Roy Shilkrot
3afe7670fe Readme update 2024-04-01 22:24:32 -04:00
Roy Shilkrot
4638ce80fe
Remove Cublas input from build script (#80)
* Remove Cublas input from build script

* Remove CUDA Toolkit installation and curl submodule
2024-04-01 21:59:37 -04:00
Roy Shilkrot
a569da2ed3
Built-in Translation (#79)
* Add translation feature and dependencies

* Add model-infos.cpp and translate_add_context to en-US.ini

* Fix formatting and whitespace issues

* Update build plugin and version, fix translation and whisper-utils

* Fix compiler warning and simplify code in transcription-filter.cpp

* Update CMakePresets.json and buildspec.json

* Fix Clang compiler warnings

* Enable QT in CMakePresets.json

* Fix compiler warnings and create missing config folder

* Fix formatting of is_lead_byte and is_trail_byte macros
2024-04-01 14:37:31 -04:00
Roy Shilkrot
0c7d7234af
Update CUDA support and model versions (#78) 2024-03-24 21:23:06 -04:00
Roy Shilkrot
17ffcfc2c1
Enable MacOS ARM64 and Windows CUDA builds (#76)
* Enable CoreML and allow fallback to CPU on MacOS ARM64

* Disable CoreML support on MacOS ARM64

* Fix build configuration for MacOS

* Update macOS build configuration based on MACOS_ARCH environment variable

* Update BuildWhispercpp.cmake to disable FMA instructions on non-Apple platforms

* Add cuBLAS support to build and package actions

* Update Cublas versions in Windows build and packaging scripts

* Update CUDA_TOOLKIT_ROOT_DIR environment variable

* Add sub-packages and non-cuda-sub-packages options to CUDA toolkit setup

* Update CUDA sub-packages in build-project.yaml

* Add "visual_studio_integration" to sub-packages in CUDA build workflow

* Fix typo in build-project.yaml

* Fix typo in CUDA build method

* Update sub-packages in CUDA toolkit installation

* Remove unnecessary CUDA sub-packages and method
2024-03-22 13:33:07 -04:00
Roy Shilkrot
7a1a6f8d69 Bump libcurl 2024-03-18 00:06:16 -04:00
Roy Shilkrot
8fe7da6d42
Fix Max Channels, Update macOS brew command and fix compiler warnings (#75) 2024-03-17 13:16:01 -04:00
Roy Shilkrot
4c15b9514c
Update Whispercpp_Build_GIT_TAG in BuildWhispercpp.cmake (#72) 2024-03-08 10:25:03 -05:00
Roy Shilkrot
d8f64971c2
Update version and Whispercpp build tag (#65) 2024-01-25 11:59:05 -05:00
Roy Shilkrot
b45b235ad6
Bump whisper.cpp. Simple settings mode (#60)
* bump whispercpp, simple settings mode

* lint
2023-12-21 11:08:36 -05:00
Roy Shilkrot
8c02e0c3fc
Fix CUDA build, shuffle whisper files around (#58)
* fix CUDA build, shuffle whisper files around

* lint
2023-11-20 09:18:06 -05:00
Roy Shilkrot
677c08c672 roll back to faster whispercpp ver 2023-11-15 22:17:38 -05:00
Roy Shilkrot
1d80602bbe
Bump whispercpp, fix mac build (#56) 2023-11-15 18:49:25 -05:00
Roy Shilkrot
ec65ffbbf7 cmake-format 2023-11-13 16:40:09 -05:00
Roy Shilkrot
dcfaddeedb add fpic to plugin-support on linux 2023-11-13 16:33:57 -05:00
Roy Shilkrot
ea34206400 bump whisper 2023-11-04 22:30:23 -04:00
Roy Shilkrot
9e8f2064a8 fetch libcurl instead of build 2023-10-17 14:17:00 -04:00
Roy Shilkrot
9299e7592e srt saving 2023-10-07 13:46:58 -04:00
Roy Shilkrot
15b6e1ed00
Merge pull request #28 from obs-ai/roy.fix_linux_crash 2023-09-28 02:04:23 -04:00
Roy Shilkrot
a2003d59db lint 2023-09-28 01:46:21 -04:00
Roy Shilkrot
280bd420fc remove blas 2023-09-28 01:45:03 -04:00
Roy Shilkrot
3fa1f11418 fix osx build 2023-09-28 00:09:56 -04:00
Roy Shilkrot
6a47a90b7f disable AVX on linux 2023-09-26 15:11:00 -04:00
Roy Shilkrot
6721b66ade lint 2023-09-25 23:58:10 -04:00
Roy Shilkrot
01412a1094 add openblas 2023-09-25 23:55:32 -04:00
Roy Shilkrot
7805574c7d solve backslarh win path problem 2023-09-20 16:18:39 -04:00
Roy Shilkrot
a025799cd6 install CUDA dlls 2023-09-20 15:50:43 -04:00
Roy Shilkrot
745937af4d openblas sha 2023-09-16 18:40:16 +03:00
Roy Shilkrot
27730fa407 add caption to stream option 2023-09-13 20:36:21 -04:00
Roy Shilkrot
06675eb0bb lint 2023-09-12 01:03:32 -04:00
Roy Shilkrot
b92bf4d36c add cuda build options 2023-09-12 01:03:05 -04:00
Roy Shilkrot
b60451f9e3 lean libcurl build 2023-09-11 23:21:48 -04:00
Roy Shilkrot
a0713f4bce fix osx linux 2023-09-11 01:14:44 -04:00
Roy Shilkrot
adb2ede905 add openblas 2023-09-11 00:48:49 -04:00
Roy Shilkrot
d794906bdc whisper universal 2023-08-13 23:53:25 +03:00
Roy Shilkrot
1b86990e91 try osx fix 2023-08-13 18:39:12 +03:00
Roy Shilkrot
e330d4e211 dont fail on patch 2023-08-13 18:00:23 +03:00
Roy Shilkrot
357b429b80 add model downloader 2023-08-13 17:55:04 +03:00
Roy Shilkrot
7023ec5152 initial 2023-08-12 23:51:51 +03:00