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/utils.h

84 lines
2.2 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 <Python.h>
#include <string.h>
char *PyMem_Strndup(const char *str, size_t len) {
if (str != NULL) {
char *copy = PyMem_New(char, len + 1);
if (copy != NULL) memcpy(copy, str, len);
copy[len] = '\0';
return copy;
}
return NULL;
}
char *PyMem_Strdup(const char *str) { return PyMem_Strndup(str, strlen(str)); }
char *reprn(char *str, size_t len) {
static char strings[10240];
static size_t current = 0;
size_t reqlen = 2;
char c, *out, *write, *begin = str, *end = str + len;
while (begin < end) {
c = *begin;
if (c == '\'') {
reqlen += 2;
} else if (c == '\r') {
reqlen += 2;
} else if (c == '\n') {
reqlen += 2;
} else if (c == '\t') {
reqlen += 2;
} else if (c < ' ') {
reqlen += 3;
} else {
reqlen++;
}
begin++;
}
if (reqlen > 10240) {
reqlen = 10240;
}
if (current + reqlen > 10240) {
current = 0;
}
begin = str;
end = str + len;
out = write = strings + current;
*write++ = '\'';
while (begin < end) {
c = *begin;
if (c == '\'') {
if (write + 5 >= strings + 10240) break;
sprintf(write, "\\'");
write += 2;
} else if (c == '\r') {
if (write + 5 >= strings + 10240) break;
sprintf(write, "\\r");
write += 2;
} else if (c == '\n') {
if (write + 5 >= strings + 10240) break;
sprintf(write, "\\n");
write += 2;
} else if (c == '\t') {
if (write + 5 >= strings + 10240) break;
sprintf(write, "\\t");
write += 2;
} else if (c < ' ') {
if (write + 6 >= strings + 10240) break;
sprintf(write, "\\x%02x", c);
write += 3;
} else {
if (write + 4 >= strings + 10240) break;
*write++ = c;
}
begin++;
}
*write++ = '\'';
*write++ = '\0';
current += (size_t)(write - out);
return out;
}
char *repr(char *str) { return reprn(str, strlen(str)); }