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/setup.py

87 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
3 years ago
#!/usr/bin/env python3
from setuptools import setup
# Available at setup time due to pyproject.toml
from pybind11.setup_helpers import Pybind11Extension, build_ext
from pybind11 import get_cmake_dir
VERSION_INFO = (1, 2, 0)
DATE_INFO = (2013, 2, 10) # YEAR, MONTH, DAY
VERSION = '.'.join(str(i) for i in VERSION_INFO)
REVISION = '%04d%02d%02d' % DATE_INFO
BUILD_INFO = "MMSeg v" + VERSION + " (" + REVISION + ")"
AUTHOR = "pluskid & kronuz & zsp007"
AUTHOR_EMAIL = 'pluskid@gmail.com'
URL = 'http://github.com/pluskid/pymmseg-cpp'
DOWNLOAD_URL = 'https://github.com/pluskid/pymmseg-cpp/archive/master.tar.gz'
LICENSE = "MIT"
PROJECT = "pymmseg"
def read(fname):
import os
try:
return open(os.path.join(os.path.dirname(__file__),
fname)).read().strip()
except IOError:
return ''
extra = {}
import sys
if sys.version_info >= (3, 0):
extra.update(use_2to3=True, )
# The main interface is through Pybind11Extension.
# * You can add cxx_std=11/14/17, and then build_ext can be removed.
# * You can set include_pybind11=false to add the include directory yourself,
# say from a submodule.
#
# Note:
# Sort input source files if you glob sources to ensure bit-for-bit
# reproducible builds (https://github.com/pybind/python_example/pull/53)
ext_modules = [
Pybind11Extension(
"mmseg",
[
'mmseg/mmseg-cpp/mmseg.cpp', 'mmseg/mmseg-cpp/algor.cpp',
'mmseg/mmseg-cpp/dict.cpp', 'mmseg/mmseg-cpp/memory.cpp'
],
include_dirs=['mmseg/mmseg-cpp'],
# Example: passing in the version to the compiled code
define_macros=[('VERSION_INFO', VERSION_INFO)],
),
]
setup(
name=PROJECT,
version=VERSION,
description=read('DESCRIPTION'),
long_description=read('README'),
author=AUTHOR,
author_email=AUTHOR_EMAIL,
url=URL,
download_url=DOWNLOAD_URL,
license=LICENSE,
keywords='mmseg chinese word segmentation tokenization',
classifiers=[
"Development Status :: 5 - Production/Stable",
"Intended Audience :: Developers",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent", "Programming Language :: Python",
"Programming Language :: Python :: 3", "Topic :: Text Processing",
"Topic :: Software Development :: Libraries :: Python Modules"
],
setup_requires=["pybind11"],
install_requires=["pybind11"],
#packages=['mmseg'],
ext_modules=ext_modules,
extras_require={"test": "pytest"},
# Currently, build_ext only provides an optional "highest supported C++
# level" feature, but in the future it may provide more features.
cmdclass={"build_ext": build_ext},
package_data={'mmseg': ['data/*.dic']},
scripts=['bin/pymmseg'],
**extra)