whisper.cpp/examples/talk-llama/unicode-data.h

18 lines
888 B
C
Raw Normal View History

#pragma once
#include <cstdint>
#include <map>
#include <utility>
#include <vector>
2024-05-12 17:12:46 +00:00
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_number;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_letter;
2024-05-12 17:12:46 +00:00
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_separator;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_whitespace;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_accent_mark;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_punctuation;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_symbol;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_control;
2024-05-12 17:12:46 +00:00
extern const std::multimap<uint32_t, uint32_t> unicode_map_nfd;
extern const std::map<char32_t, char32_t> unicode_map_lowercase;