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/utils/spm_encode

102 lines
3.4 KiB

#!/usr/bin/env python3
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
# Copyright (c) Facebook, Inc. and its affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in
# https://github.com/pytorch/fairseq/blob/master/LICENSE
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
import argparse
import contextlib
import sys
import sentencepiece as spm
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--model", required=True,
help="sentencepiece model to use for encoding")
parser.add_argument("--inputs", nargs="+", default=['-'],
help="input files to filter/encode")
parser.add_argument("--outputs", nargs="+", default=['-'],
help="path to save encoded outputs")
parser.add_argument("--output_format", choices=["piece", "id"], default="piece")
parser.add_argument("--min-len", type=int, metavar="N",
help="filter sentence pairs with fewer than N tokens")
parser.add_argument("--max-len", type=int, metavar="N",
help="filter sentence pairs with more than N tokens")
args = parser.parse_args()
assert len(args.inputs) == len(args.outputs), \
"number of input and output paths should match"
sp = spm.SentencePieceProcessor()
sp.Load(args.model)
if args.output_format == "piece":
def encode(l):
return sp.EncodeAsPieces(l)
elif args.output_format == "id":
def encode(l):
return list(map(str, sp.EncodeAsIds(l)))
else:
raise NotImplementedError
if args.min_len is not None or args.max_len is not None:
def valid(line):
return (
(args.min_len is None or len(line) >= args.min_len) and
(args.max_len is None or len(line) <= args.max_len)
)
else:
def valid(lines):
return True
with contextlib.ExitStack() as stack:
inputs = [
stack.enter_context(open(input, "r", encoding="utf-8"))
if input != "-" else sys.stdin
for input in args.inputs
]
outputs = [
stack.enter_context(open(output, "w", encoding="utf-8"))
if output != "-" else sys.stdout
for output in args.outputs
]
stats = {
"num_empty": 0,
"num_filtered": 0,
}
def encode_line(line):
line = line.strip()
if len(line) > 0:
line = encode(line)
if valid(line):
return line
else:
stats["num_filtered"] += 1
else:
stats["num_empty"] += 1
return None
for i, lines in enumerate(zip(*inputs), start=1):
enc_lines = list(map(encode_line, lines))
if not any(enc_line is None for enc_line in enc_lines):
for enc_line, output_h in zip(enc_lines, outputs):
print(" ".join(enc_line), file=output_h)
if i % 10000 == 0:
print("processed {} lines".format(i), file=sys.stderr)
print("skipped {} empty lines".format(stats["num_empty"]), file=sys.stderr)
print("filtered {} lines".format(stats["num_filtered"]), file=sys.stderr)
if __name__ == "__main__":
main()