ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-14 04:58:06 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp (#3084)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-04-28 16:40:23 +03:00
committed by GitHub
parent 28dcdff4c5
commit f3c42399a3
36 changed files with 16940 additions and 12400 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/talk-llama/unicode.cpp
View File

@ -618,7 +618,14 @@ std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8) {
result.reserve(utf8.size());
size_t offset = 0;
while (offset < utf8.size()) {
result.push_back(unicode_cpt_from_utf8(utf8, offset));
try {
result.push_back(unicode_cpt_from_utf8(utf8, offset));
}
catch (const std::invalid_argument & /*ex*/) {
// Silently ignore invalid UTF-8 input to avoid leaking the exception beyond llama_tokenize
++offset;
result.emplace_back(0xFFFD); // replacement character
}
}
return result;
}
@ -701,7 +708,7 @@ std::vector<std::string> unicode_regex_split(const std::string & text, const std
const auto cpts = unicode_cpts_from_utf8(text);
// generate a "collapsed" representation of the text, where all codepoints are replaced by a single byte
// ref: https://github.com/ggerganov/llama.cpp/pull/6920#issuecomment-2081479935
// ref: https://github.com/ggml-org/llama.cpp/pull/6920#issuecomment-2081479935
std::string text_collapsed;
if (need_collapse) {
// collapse all unicode categories