mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-12-28 08:18:51 +00:00
3e5c7feeff
* whisper : add grammar-based sampling * build : fix after master merge * command : fix exception when recognizing the command * whisper : fine-tuning grammar functionality * command : grammar-related improvements - option to read grammar from file - add sample grammars for colors and chess moves - fine-tune the performance further * grammars : add assistant + update comments * command : enable beam-search, add "no_timestamps", add "context", add p * whisper : remove comment --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
30 lines
895 B
C++
30 lines
895 B
C++
// Implements a parser for an extended Backus-Naur form (BNF), producing the
|
|
// binary context-free grammar format specified by whisper.h. Supports character
|
|
// ranges, grouping, and repetition operators. As an example, a grammar for
|
|
// arithmetic might look like:
|
|
//
|
|
// root ::= expr
|
|
// expr ::= term ([-+*/] term)*
|
|
// term ::= num | "(" space expr ")" space
|
|
// num ::= [0-9]+ space
|
|
// space ::= [ \t\n]*
|
|
|
|
#pragma once
|
|
#include "whisper.h"
|
|
#include <vector>
|
|
#include <map>
|
|
#include <cstdint>
|
|
#include <string>
|
|
|
|
namespace grammar_parser {
|
|
struct parse_state {
|
|
std::map<std::string, uint32_t> symbol_ids;
|
|
std::vector<std::vector<whisper_grammar_element>> rules;
|
|
|
|
std::vector<const whisper_grammar_element *> c_rules() const;
|
|
};
|
|
|
|
parse_state parse(const char * src);
|
|
void print_grammar(FILE * file, const parse_state & state);
|
|
}
|