You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/third_party/pymmseg-cpp/mmseg/mmseg-cpp/mmseg.cpp

102 lines
2.8 KiB

E2E/Streaming Transformer/Conformer ASR (#578) * add cmvn and label smoothing loss layer * add layer for transformer * add glu and conformer conv * add torch compatiable hack, mask funcs * not hack size since it exists * add test; attention * add attention, common utils, hack paddle * add audio utils * conformer batch padding mask bug fix #223 * fix typo, python infer fix rnn mem opt name error and batchnorm1d, will be available at 2.0.2 * fix ci * fix ci * add encoder * refactor egs * add decoder * refactor ctc, add ctc align, refactor ckpt, add warmup lr scheduler, cmvn utils * refactor docs * add fix * fix readme * fix bugs, refactor collator, add pad_sequence, fix ckpt bugs * fix docstring * refactor data feed order * add u2 model * refactor cmvn, test * add utils * add u2 config * fix bugs * fix bugs * fix autograd maybe has problem when using inplace operation * refactor data, build vocab; add format data * fix text featurizer * refactor build vocab * add fbank, refactor feature of speech * refactor audio feat * refactor data preprare * refactor data * model init from config * add u2 bins * flake8 * can train * fix bugs, add coverage, add scripts * test can run * fix data * speed perturb with sox * add spec aug * fix for train * fix train logitc * fix logger * log valid loss, time dataset process * using np for speed perturb, remove some debug log of grad clip * fix logger * fix build vocab * fix logger name * using module logger as default * fix * fix install * reorder imports * fix board logger * fix logger * kaldi fbank and mfcc * fix cmvn and print prarams * fix add_eos_sos and cmvn * fix cmvn compute * fix logger and cmvn * fix subsampling, label smoothing loss, remove useless * add notebook test * fix log * fix tb logger * multi gpu valid * fix log * fix log * fix config * fix compute cmvn, need paddle 2.1 * add cmvn notebook * fix layer tools * fix compute cmvn * add rtf * fix decoding * fix layer tools * fix log, add avg script * more avg and test info * fix dataset pickle problem; using 2.1 paddle; num_workers can > 0; ckpt save in exp dir;fix setup.sh; * add vimrc * refactor tiny script, add transformer and stream conf * spm demo; librisppech scripts and confs * fix log * add librispeech scripts * refactor data pipe; fix conf; fix u2 default params * fix bugs * refactor aishell scripts * fix test * fix cmvn * fix s0 scripts * fix ds2 scripts and bugs * fix dev & test dataset filter * fix dataset filter * filter dev * fix ckpt path * filter test, since librispeech will cause OOM, but all test wer will be worse, since mismatch train with test * add comment * add syllable doc * fix ds2 configs * add doc * add pypinyin tools * fix decoder using blank_id=0 * mmseg with pybind11 * format code
4 years ago
#include <pybind11/pybind11.h>
#include <iostream>
#include <string>
#include "algor.h"
#include "dict.h"
#include "token.h"
#include "utils.h"
namespace py = pybind11;
#define STRINGIFY(x) #x
#define MACRO_STRINGIFY(x) STRINGIFY(x)
struct Token {
const char *text;
int offset;
int length;
};
PYBIND11_MODULE(mmseg, m) {
// String literal: https://en.cppreference.com/w/cpp/language/string_literal
m.doc() = R"pbdoc(
MMSeg pybind
)pbdoc";
m.def("load_chars", [](const char *path) {
if (rmmseg::dict::load_chars(path)) {
return true;
}
return false;
});
m.def("load_words", [](const char *path) {
if (rmmseg::dict::load_words(path)) {
return true;
}
return false;
});
m.def("add", [](const char *word, int len, int freq) {
/*
* Add a word to the in-memory dictionary.
*
* - word is a String.
* - length is number of characters (not number of
* bytes) of the
* word to be added.
* - freq is the frequency of the word. This is only
* used when
* it is a one-character word.
*/
rmmseg::Word *w = rmmseg::make_word(word, len, freq, strlen(word));
rmmseg::dict::add(w);
});
m.def("has_word", [](const char *word) {
if (rmmseg::dict::get(word, static_cast<int>(strlen(word)))) {
return true;
}
return false;
});
py::class_<rmmseg::Token>(m, "Token")
.def(py::init([](std::string str) {
return rmmseg::Token(str.c_str(), str.size());
}))
.def_property_readonly("text",
[](rmmseg::Token &self) {
return std::string(self.text, self.length);
})
.def_readonly("length", &rmmseg::Token::length)
.def("__repr__",
[](rmmseg::Token &self) {
return "<Token " + std::string(self.text, self.length) + " " +
std::to_string(self.length) + ">";
})
.def("__str__", [](rmmseg::Token &self) {
return std::string(self.text, self.length);
});
py::class_<rmmseg::Algorithm>(m, "Algorithm")
//.def(py::init<const char *, int>(), py::keep_alive<1, 2>())
.def(py::init([](std::string str) { return rmmseg::Algorithm(str); }))
.def("get_text",
[](rmmseg::Algorithm &self) { return self.get_text(); },
py::return_value_policy::reference)
.def("next_token",
[](rmmseg::Algorithm &self) { return self.next_token(); });
#ifdef VERSION_INFO
m.attr("__version__") = MACRO_STRINGIFY(VERSION_INFO);
#else
m.attr("__version__") = "dev";
#endif
}