Update OCR Plugin features and whitelist characters (#20)

README.md

@@ -47,7 +47,7 @@ OCR Plugin enables many use cases for enhancing your stream or recording:
 ### Features
 Available now:
  - Add OCR Filter to any source with image or video output
- - Choose from English model or Scoreboard model
+ - Choose from Scoreboard model or English, French, Spanish, German, Chinese, Japanese, Arabic, Turkish, Portugese, Hindi, Russian and Italian
  - Output OCR result to an OBS Text Source
  - Choose the segmentation mode: Word, Line, Page, etc.
  - "Semantic Smoothing": getting more consistent outputs with higher accuracy and confidence by "averaging" several text outputs
@@ -71,10 +71,11 @@ Coming soon:
 
 Check out our other plugins:
 - [Background Removal](https://github.com/occ-ai/obs-backgroundremoval) removes background from webcam without a green screen.
-- 🚧 Experimental 🚧 [CleanStream](https://github.com/occ-ai/obs-cleanstream) for real-time filler word (uh,um) and profanity removal from live audio stream
+- [Detect](https://github.com/occ-ai/obs-detect) will detect and track >80 types of objects in any OBS source.
 - [LocalVocal](https://github.com/occ-ai/obs-localvocal) speech AI assistant plugin for real-time, local transcription (captions), translation and more language functions
 - [Polyglot](https://github.com/occ-ai/obs-polyglot) translation AI plugin for real-time, local translation to hunderds of languages
 - [URL/API Source](https://github.com/occ-ai/obs-urlsource) will connect to any URL/API HTTP and get the data/image/audio to your scene.
+- 🚧 Experimental 🚧 [CleanStream](https://github.com/occ-ai/obs-cleanstream) for real-time filler word (uh,um) and profanity removal from live audio stream
 
 If you like this work, which is given to you completely free of charge, please consider supporting it https://github.com/sponsors/royshil or https://www.patreon.com/RoyShilkrot
 

src/consts.h

@@ -6,4 +6,25 @@ const char *const PLUGIN_INFO_TEMPLATE =
 	"<a href=\"https://github.com/occ-ai\">OCC AI</a> ❤️ "
 	"<a href=\"https://www.patreon.com/RoyShilkrot\">Support & Follow</a>";
 
+const char *const WHITELIST_CHARS_ENGLISH =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!@#$%^&*()_+-=[]{}|;':\",./<>?`~\\ ";
+// add french characters with accents
+const char *const WHITELIST_CHARS_FRENCH =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!@#$%^&*()_+-=[]{}|;':\",./<>?`~\\éèêàâùûç ";
+// add german characters with umlauts
+const char *const WHITELIST_CHARS_GERMAN =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!@#$%^&*()_+-=[]{}|;':\",./<>?`~\\äöüß ";
+// add spanish characters with accents
+const char *const WHITELIST_CHARS_SPANISH =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!@#$%^&*()_+-=[]{}|;':\",./<>?`~\\áéíóúüñ ";
+// add italian characters with accents
+const char *const WHITELIST_CHARS_ITALIAN =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!@#$%^&*()_+-=[]{}|;':\",./<>?`~\\àèéìòù ";
+// add portuguese characters with accents
+const char *const WHITELIST_CHARS_PORTUGUESE =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!@#$%^&*()_+-=[]{}|;':\",./<>?`~\\áàãâéêíóôõúüç ";
+// add russian characters
+const char *const WHITELIST_CHARS_RUSSIAN =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!@#$%^&*()_+-=[]{}|;':\",./<>?`~\\абвгдеёжзийклмнопрстуфхцчшщъыьэюя ";
+
 #endif /* CONSTS_H */

src/ocr-filter.cpp

@@ -83,11 +83,11 @@ obs_properties_t *ocr_filter_properties(void *data)
 
 	// scan the tessdata folder for files using std::filesystem
 	std::string tessdata_folder = obs_module_file("tessdata");
-	obs_log(LOG_INFO, "Scanning tessdata folder: %s", tessdata_folder.c_str());
+	obs_log(LOG_DEBUG, "Scanning tessdata folder: %s", tessdata_folder.c_str());
 	for (const auto &entry : std::filesystem::directory_iterator(tessdata_folder)) {
 		std::string filename = entry.path().filename().string();
 		if (filename.find(".traineddata") != std::string::npos) {
-			obs_log(LOG_INFO, "Found traineddata file: %s", filename.c_str());
+			obs_log(LOG_DEBUG, "Found traineddata file: %s", filename.c_str());
 			std::string language = filename.substr(0, filename.find(".traineddata"));
 			obs_property_list_add_string(lang_list, language.c_str(), language.c_str());
 		}
@@ -295,9 +295,8 @@ void ocr_filter_defaults(obs_data_t *settings)
 	obs_data_set_default_int(settings, "rescale_target_size", 35);
 	obs_data_set_default_string(settings, "text_sources", "none");
 	obs_data_set_default_string(settings, "text_detection_mask_sources", "none");
-	obs_data_set_default_string(
-		settings, "char_whitelist",
-		"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz.,:;!?-()[]{}<>|/@#$%&*+=_~ ");
+	obs_data_set_default_string(settings, "char_whitelist",
+				    WHITELIST_CHARS_ENGLISH); // default to english characters
 	obs_data_set_default_int(settings, "conf_threshold", 50);
 	obs_data_set_default_bool(settings, "enable_smoothing", false);
 	obs_data_set_default_int(settings, "word_length", 5);