|
|
|
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
|
|
|
|
#
|
|
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
|
|
# you may not use this file except in compliance with the License.
|
|
|
|
# You may obtain a copy of the License at
|
|
|
|
#
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
#
|
|
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
# See the License for the specific language governing permissions and
|
|
|
|
# limitations under the License.
|
|
|
|
"""Script to build and install decoder package."""
|
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
|
|
|
import argparse
|
|
|
|
import glob
|
|
|
|
import multiprocessing.pool
|
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
|
|
|
import os
|
|
|
|
import platform
|
|
|
|
import sys
|
|
|
|
|
|
|
|
from setuptools import distutils
|
|
|
|
from setuptools import Extension
|
|
|
|
from setuptools import setup
|
|
|
|
|
|
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
|
|
parser.add_argument(
|
|
|
|
"--num_processes",
|
|
|
|
default=1,
|
|
|
|
type=int,
|
|
|
|
help="Number of cpu processes to build package. (default: %(default)d)")
|
|
|
|
args = parser.parse_known_args()
|
|
|
|
|
|
|
|
# reconstruct sys.argv to pass to setup below
|
|
|
|
sys.argv = [sys.argv[0]] + args[1]
|
|
|
|
|
|
|
|
|
|
|
|
# monkey-patch for parallel compilation
|
|
|
|
# See: https://stackoverflow.com/a/13176803
|
|
|
|
def parallelCCompile(self,
|
|
|
|
sources,
|
|
|
|
output_dir=None,
|
|
|
|
macros=None,
|
|
|
|
include_dirs=None,
|
|
|
|
debug=0,
|
|
|
|
extra_preargs=None,
|
|
|
|
extra_postargs=None,
|
|
|
|
depends=None):
|
|
|
|
# those lines are copied from distutils.ccompiler.CCompiler directly
|
|
|
|
macros, objects, extra_postargs, pp_opts, build = self._setup_compile(
|
|
|
|
output_dir, macros, include_dirs, sources, depends, extra_postargs)
|
|
|
|
cc_args = self._get_cc_args(pp_opts, debug, extra_preargs)
|
|
|
|
|
|
|
|
# parallel code
|
|
|
|
def _single_compile(obj):
|
|
|
|
try:
|
|
|
|
src, ext = build[obj]
|
|
|
|
except KeyError:
|
|
|
|
return
|
|
|
|
self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
|
|
|
|
|
|
|
|
# convert to list, imap is evaluated on-demand
|
|
|
|
thread_pool = multiprocessing.pool.ThreadPool(args[0].num_processes)
|
|
|
|
list(thread_pool.imap(_single_compile, objects))
|
|
|
|
return objects
|
|
|
|
|
|
|
|
|
|
|
|
def compile_test(header, library):
|
|
|
|
dummy_path = os.path.join(os.path.dirname(__file__), "dummy")
|
|
|
|
command = "bash -c \"g++ -include " + header \
|
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
|
|
|
+ " -l" + library + " -x c++ - <<<'int main() {}' -o " \
|
|
|
|
+ dummy_path + " >/dev/null 2>/dev/null && rm " \
|
|
|
|
+ dummy_path + " 2>/dev/null\""
|
|
|
|
return os.system(command) == 0
|
|
|
|
|
|
|
|
|
|
|
|
# hack compile to support parallel compiling
|
|
|
|
distutils.ccompiler.CCompiler.compile = parallelCCompile
|
|
|
|
|
|
|
|
FILES = glob.glob('kenlm/util/*.cc') \
|
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
|
|
|
+ glob.glob('kenlm/lm/*.cc') \
|
|
|
|
+ glob.glob('kenlm/util/double-conversion/*.cc')
|
|
|
|
|
|
|
|
FILES += glob.glob('openfst-1.6.3/src/lib/*.cc')
|
|
|
|
|
|
|
|
# yapf: disable
|
|
|
|
FILES = [
|
|
|
|
fn for fn in FILES if not (fn.endswith('main.cc') or fn.endswith('test.cc')
|
|
|
|
or fn.endswith('unittest.cc'))
|
|
|
|
]
|
|
|
|
# yapf: enable
|
|
|
|
|
|
|
|
LIBS = ['stdc++']
|
|
|
|
if platform.system() != 'Darwin':
|
|
|
|
LIBS.append('rt')
|
|
|
|
|
|
|
|
ARGS = ['-O3', '-DNDEBUG', '-DKENLM_MAX_ORDER=6', '-std=c++11']
|
|
|
|
|
|
|
|
if compile_test('zlib.h', 'z'):
|
|
|
|
ARGS.append('-DHAVE_ZLIB')
|
|
|
|
LIBS.append('z')
|
|
|
|
|
|
|
|
if compile_test('bzlib.h', 'bz2'):
|
|
|
|
ARGS.append('-DHAVE_BZLIB')
|
|
|
|
LIBS.append('bz2')
|
|
|
|
|
|
|
|
if compile_test('lzma.h', 'lzma'):
|
|
|
|
ARGS.append('-DHAVE_XZLIB')
|
|
|
|
LIBS.append('lzma')
|
|
|
|
|
|
|
|
os.system('swig -python -c++ ./decoders.i')
|
|
|
|
|
|
|
|
decoders_module = [
|
|
|
|
Extension(
|
|
|
|
name='_paddlespeech_ctcdecoders',
|
|
|
|
sources=FILES + glob.glob('*.cxx') + glob.glob('*.cpp'),
|
|
|
|
language='c++',
|
|
|
|
include_dirs=[
|
|
|
|
'.',
|
|
|
|
'kenlm',
|
|
|
|
'openfst-1.6.3/src/include',
|
|
|
|
'ThreadPool',
|
|
|
|
],
|
|
|
|
libraries=LIBS,
|
|
|
|
extra_compile_args=ARGS)
|
|
|
|
]
|
|
|
|
|
|
|
|
setup(
|
|
|
|
name='paddlespeech_ctcdecoders',
|
|
|
|
version='0.2.0',
|
|
|
|
description="CTC decoders in paddlespeech",
|
|
|
|
author="PaddlePaddle Speech and Language Team",
|
|
|
|
author_email="paddlesl@baidu.com",
|
|
|
|
url="https://github.com/PaddlePaddle/PaddleSpeech",
|
|
|
|
license='Apache 2.0, GNU Lesser General Public License v3 (LGPLv3) (LGPL-3)',
|
|
|
|
ext_modules=decoders_module,
|
|
|
|
py_modules=['paddlespeech_ctcdecoders'])
|