mirrors/obs-localvocal
1
0
Fork 0
mirror of https://github.com/occ-ai/obs-localvocal synced 2024-11-07 18:57:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #13 from royshil/roy.add_caption_to_stream

Browse Source 
Add caption to stream option
This commit is contained in:
Roy Shilkrot 2023-09-14 10:53:04 -04:00 committed by GitHub
commit 166f6f391d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 14 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cmake/BuildWhispercpp.cmake
View File

@ -72,7 +72,7 @@ else()
Whispercpp_Build Whispercpp_Build
DOWNLOAD_EXTRACT_TIMESTAMP true DOWNLOAD_EXTRACT_TIMESTAMP true
GIT_REPOSITORY https://github.com/ggerganov/whisper.cpp.git GIT_REPOSITORY https://github.com/ggerganov/whisper.cpp.git
GIT_TAG 7b374c9ac9b9861bb737eec060e4dfa29d229259 GIT_TAG 3fec2119e6b52d1381b02a0fbf281b1b34728c25
BUILD_COMMAND ${CMAKE_COMMAND} --build <BINARY_DIR> --config ${Whispercpp_BUILD_TYPE} BUILD_COMMAND ${CMAKE_COMMAND} --build <BINARY_DIR> --config ${Whispercpp_BUILD_TYPE}
BUILD_BYPRODUCTS <INSTALL_DIR>/lib/static/${CMAKE_STATIC_LIBRARY_PREFIX}whisper${CMAKE_STATIC_LIBRARY_SUFFIX} BUILD_BYPRODUCTS <INSTALL_DIR>/lib/static/${CMAKE_STATIC_LIBRARY_PREFIX}whisper${CMAKE_STATIC_LIBRARY_SUFFIX}
CMAKE_GENERATOR ${CMAKE_GENERATOR} CMAKE_GENERATOR ${CMAKE_GENERATOR}

1
src/transcription-filter-data.h
View File

@ -50,6 +50,7 @@ struct transcription_filter_data {
bool vad_enabled; bool vad_enabled;
int log_level; int log_level;
bool log_words; bool log_words;
bool caption_to_stream;
bool active = false; bool active = false;
// Text source to output the subtitles // Text source to output the subtitles

13
src/transcription-filter.cpp
View File

@ -1,4 +1,5 @@
#include <obs-module.h> #include <obs-module.h>
#include <obs-frontend-api.h>
#include "plugin-support.h" #include "plugin-support.h"
#include "transcription-filter.h" #include "transcription-filter.h"
@ -177,6 +178,13 @@ void acquire_weak_text_source_ref(struct transcription_filter_data *gf)
void set_text_callback(struct transcription_filter_data *gf, const std::string &str) void set_text_callback(struct transcription_filter_data *gf, const std::string &str)
{ {
if (gf->caption_to_stream) {
obs_output_t *streaming_output = obs_frontend_get_streaming_output();
if (streaming_output) {
obs_output_output_caption_text1(streaming_output, str.c_str());
obs_output_release(streaming_output);
}
}
if (gf->output_file_path != "" && !gf->text_source_name) { if (gf->output_file_path != "" && !gf->text_source_name) {
// Write to file, do not append // Write to file, do not append
std::ofstream output_file(gf->output_file_path, std::ios::out | std::ios::trunc); std::ofstream output_file(gf->output_file_path, std::ios::out | std::ios::trunc);
@ -220,6 +228,7 @@ void transcription_filter_update(void *data, obs_data_t *s)
gf->log_level = (int)obs_data_get_int(s, "log_level"); gf->log_level = (int)obs_data_get_int(s, "log_level");
gf->vad_enabled = obs_data_get_bool(s, "vad_enabled"); gf->vad_enabled = obs_data_get_bool(s, "vad_enabled");
gf->log_words = obs_data_get_bool(s, "log_words"); gf->log_words = obs_data_get_bool(s, "log_words");
gf->caption_to_stream = obs_data_get_bool(s, "caption_to_stream");
obs_log(gf->log_level, "transcription_filter: update text source"); obs_log(gf->log_level, "transcription_filter: update text source");
// update the text source // update the text source
@ -454,8 +463,9 @@ void transcription_filter_deactivate(void *data)
void transcription_filter_defaults(obs_data_t *s) void transcription_filter_defaults(obs_data_t *s)
{ {
obs_data_set_default_bool(s, "vad_enabled", true); obs_data_set_default_bool(s, "vad_enabled", true);
obs_data_set_default_int(s, "log_level", LOG_INFO); obs_data_set_default_int(s, "log_level", LOG_DEBUG);
obs_data_set_default_bool(s, "log_words", true); obs_data_set_default_bool(s, "log_words", true);
obs_data_set_default_bool(s, "caption_to_stream", false);
obs_data_set_default_string(s, "whisper_model_path", "models/ggml-tiny.en.bin"); obs_data_set_default_string(s, "whisper_model_path", "models/ggml-tiny.en.bin");
obs_data_set_default_string(s, "whisper_language_select", "en"); obs_data_set_default_string(s, "whisper_language_select", "en");
obs_data_set_default_string(s, "subtitle_sources", "none"); obs_data_set_default_string(s, "subtitle_sources", "none");
@ -497,6 +507,7 @@ obs_properties_t *transcription_filter_properties(void *data)
obs_property_list_add_int(list, "INFO", LOG_INFO); obs_property_list_add_int(list, "INFO", LOG_INFO);
obs_property_list_add_int(list, "WARNING", LOG_WARNING); obs_property_list_add_int(list, "WARNING", LOG_WARNING);
obs_properties_add_bool(ppts, "log_words", "Log output words"); obs_properties_add_bool(ppts, "log_words", "Log output words");
obs_properties_add_bool(ppts, "caption_to_stream", "Stream captions");
obs_property_t *subs_output = obs_property_t *subs_output =
obs_properties_add_list(ppts, "subtitle_sources", "Subtitles Output", obs_properties_add_list(ppts, "subtitle_sources", "Subtitles Output",