Commit Graph

17 Commits

Author SHA1 Message Date
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
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
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
069cba1c7a Update translation strings for multiple locales 2024-04-02 00:01:01 -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
8b4471fad4
Update save_srt option and add truncate_output_file option (#64)
* Update save_srt option and add truncate_output_file option

* Refactor code for readability and maintainability

* Update clang-format version to 16.0.5

* Update .clang-format and model-downloader-ui.cpp

* Fix is_lead_byte and is_trail_byte macros
2024-01-25 11:44:05 -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
465193a12b adding min sub duration 2023-10-29 00:26:36 -04:00
Roy Shilkrot
82a473fabb add file rename 2023-10-12 10:45:34 -04:00
Roy Shilkrot
9299e7592e srt saving 2023-10-07 13:46:58 -04:00
Roy Shilkrot
1b6da3c0f9 Locale and translations 2023-10-04 22:12:17 -04:00
Roy Shilkrot
b14ba3e93f attempt fix 2023-08-20 01:25:19 +03:00
Roy Shilkrot
7023ec5152 initial 2023-08-12 23:51:51 +03:00
Roy Shilkrot
ad7cb94c55
Initial commit 2023-08-10 22:05:20 +03:00