vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-15 11:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixed a tts parsing bug

Browse source
This commit is contained in:
Concedo 2025-01-18 10:33:42 +08:00
parent 60308ed9dd
commit 65c5c77a16
1 changed files with 9 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

12
otherarch/tts_adapter.cpp
View file

@ -336,9 +336,14 @@ static std::string process_text(const std::string & text, TTS_VER ver) {
std::transform(processed_text.begin(), processed_text.end(), std::transform(processed_text.begin(), processed_text.end(),
processed_text.begin(), ::tolower); processed_text.begin(), ::tolower);
// replace multiple punctuation with single
processed_text = std::regex_replace(processed_text, std::regex(R"(([,.!?])\1+)"), "$1");
//handle words connected by periods, replace the matches with " dot ".
processed_text = std::regex_replace(processed_text, std::regex(R"((\S)\.(\S))"), "$1 dot $2");
if(ver==TTS_VER_2) if(ver==TTS_VER_2)
{ {
std::regex special_chars(R"([-_/,\.\\])"); std::regex special_chars(R"([\(\)\[\]\{\}\:-_/,\.\\])");
processed_text = std::regex_replace(processed_text, special_chars, " "); processed_text = std::regex_replace(processed_text, special_chars, " ");
std::regex non_alpha(R"([^a-z\s])"); std::regex non_alpha(R"([^a-z\s])");
processed_text = std::regex_replace(processed_text, non_alpha, ""); processed_text = std::regex_replace(processed_text, non_alpha, "");
@ -347,7 +352,7 @@ static std::string process_text(const std::string & text, TTS_VER ver) {
processed_text = std::regex_replace(processed_text, std::regex(R"(^\s+|\s+$)"), ""); processed_text = std::regex_replace(processed_text, std::regex(R"(^\s+|\s+$)"), "");
processed_text = std::regex_replace(processed_text, std::regex(R"(\s)"), "<|text_sep|>"); processed_text = std::regex_replace(processed_text, std::regex(R"(\s)"), "<|text_sep|>");
} else { } else {
std::regex special_chars(R"([-_/\\])"); std::regex special_chars(R"([\(\)\[\]\{\}\:-_/\\])");
processed_text = std::regex_replace(processed_text, special_chars, " "); processed_text = std::regex_replace(processed_text, special_chars, " ");
std::regex non_alpha(R"([^a-z\s.,?!])"); std::regex non_alpha(R"([^a-z\s.,?!])");
processed_text = std::regex_replace(processed_text, non_alpha, ""); processed_text = std::regex_replace(processed_text, non_alpha, "");
@ -647,11 +652,12 @@ tts_generation_outputs ttstype_generate(const tts_generation_inputs inputs)
// convert the input text into the necessary format expected by OuteTTS // convert the input text into the necessary format expected by OuteTTS
std::string prompt_clean = process_text(prompt,ttsver); std::string prompt_clean = process_text(prompt,ttsver);
bool empty_check = (process_text(prompt,TTS_VER_2).size()==0); //if there is no audio, will crash, so prevent that
//further clean it by keeping only the last 300 words //further clean it by keeping only the last 300 words
prompt_clean = trim_words(prompt_clean,(ttsver==TTS_VER_3?"<|space|>":"<|text_sep|>"),300); prompt_clean = trim_words(prompt_clean,(ttsver==TTS_VER_3?"<|space|>":"<|text_sep|>"),300);
if(prompt_clean.size()==0) if(empty_check)
{ {
//no input //no input
if(!inputs.quiet) if(!inputs.quiet)