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

Browse Source
This commit is contained in:
Georgi Gerganov
2024-07-08 14:14:17 +03:00
parent d3f6c34976
commit dbf9c15e30
7 changed files with 3226 additions and 635 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
examples/talk-llama/unicode.cpp
View File

@ -23,7 +23,7 @@ static std::string unicode_cpts_to_utf8(const std::vector<uint32_t> & cps) {
return result;
}
static uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) {
uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) {
assert(offset < utf8.size());
if (!(utf8[offset + 0] & 0x80)) {
auto result = utf8[offset + 0];
@ -232,8 +232,7 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
};
auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : undef;
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
};
size_t _prev_end = offset_ini;
@ -295,9 +294,9 @@ static std::vector<size_t> unicode_regex_split_custom_gpt2(const std::string & t
continue;
}
// regex: <space>?[^\s\p{L}\p{N}]+
if (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
pos += (cpt == ' ');
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
flags2 = _get_flags(++pos);
}
_add_token(pos);
@ -351,8 +350,7 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
};
auto _get_flags = [&] (const size_t pos) -> codepoint_flags {
static const codepoint_flags undef(codepoint_flags::UNDEFINED);
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : undef;
return (offset_ini <= pos && pos < offset_end) ? unicode_cpt_flags(cpts[pos]) : codepoint_flags{};
};
size_t _prev_end = offset_ini;
@ -394,8 +392,8 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
}
}
// regex: [^\r\n\p{L}\p{N}]?\p{L}+ //####FIXME: the first \p{L} is correct?
if (!(cpt == '\r' || cpt == '\n' || /*flags.is_letter |*/ flags.is_number)) {
// regex: [^\r\n\p{L}\p{N}]?\p{L}+
if (!(cpt == '\r' || cpt == '\n' || flags.is_number)) {
if (flags.is_letter || _get_flags(pos+1).is_letter) { // one or more letters
pos++;
while (_get_flags(pos).is_letter) {
@ -421,9 +419,9 @@ static std::vector<size_t> unicode_regex_split_custom_llama3(const std::string &
// regex: <space>?[^\s\p{L}\p{N}]+[\r\n]*
auto flags2 = (cpt == ' ' ? _get_flags(pos+1) : flags);
if (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
if (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags.as_uint()) {
pos += (cpt == ' ');
while (!(flags2.is_whitespace || flags2.is_letter || flags2.is_number || flags2.is_undefined)) {
while (!(flags2.is_whitespace | flags2.is_letter | flags2.is_number) && flags2.as_uint()) {
flags2 = _get_flags(++pos);
}
uint32_t cpt2 = _get_cpt(pos);