ParakeetRebeccaRosario/setup.py

100 lines
2.8 KiB
Python
Raw Normal View History

2020-02-26 21:03:51 +08:00
# Copyright (c) 2020 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.
import io
2021-08-17 15:29:30 +08:00
import os
2019-11-22 11:32:59 +08:00
import re
2021-08-17 15:29:30 +08:00
from setuptools import find_packages
from setuptools import setup
2019-11-22 11:32:59 +08:00
2020-02-26 21:03:51 +08:00
2019-11-22 11:32:59 +08:00
def read(*names, **kwargs):
with io.open(
2020-02-26 21:03:51 +08:00
os.path.join(os.path.dirname(__file__), *names),
encoding=kwargs.get("encoding", "utf8")) as fp:
2019-11-22 11:32:59 +08:00
return fp.read()
def find_version(*file_paths):
version_file = read(*file_paths)
version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]",
version_file, re.M)
if version_match:
return version_match.group(1)
raise RuntimeError("Unable to find version string.")
2020-02-26 21:03:51 +08:00
2019-11-22 11:32:59 +08:00
VERSION = find_version('parakeet', '__init__.py')
long_description = read("README.md")
2020-12-20 14:25:56 +08:00
2019-11-22 11:32:59 +08:00
setup_info = dict(
# Metadata
2020-12-20 14:15:17 +08:00
name='paddle-parakeet',
2019-11-22 11:32:59 +08:00
version=VERSION,
author='PaddleSL Team',
author_email='',
url='https://github.com/PaddlePaddle',
description='Speech synthesis tools and models based on Paddlepaddle',
long_description=long_description,
long_description_content_type="text/markdown",
2019-11-22 11:32:59 +08:00
license='Apache 2',
2020-12-19 18:55:42 +08:00
python_requires='>=3.6',
2019-11-22 11:32:59 +08:00
install_requires=[
2020-02-26 21:03:51 +08:00
'numpy',
'nltk',
'inflect',
'librosa',
'unidecode',
add ge2e and tacotron2_aishell3 example (#107) * hacky thing, add tone support for acoustic model * fix experiments for waveflow and wavenet, only write visual log in rank-0 * use emb add in tacotron2 * 1. remove space from numericalized representation; 2. fix decoder paddign mask's unsqueeze dim. * remove bn in postnet * refactoring code * add an option to normalize volume when loading audio. * add an embedding layer. * 1. change the default min value of LogMagnitude to 1e-5; 2. remove stop logit prediction from tacotron2 model. * WIP: baker * add ge2e * fix lstm speaker encoder * fix lstm speaker encoder * fix speaker encoder and add support for 2 more datasets * simplify visualization code * add a simple strategy to support multispeaker for tacotron. * add vctk example for refactored tacotron * fix indentation * fix class name * fix visualizer * fix root path * fix root path * fix root path * fix typos * fix bugs * fix text log extention name * add example for baker and aishell3 * update experiment and display * format code for tacotron_vctk, add plot_waveform to display * add new trainer * minor fix * add global condition support for tacotron2 * add gst layer * add 2 frontend * fix fmax for example/waveflow * update collate function, data loader not does not convert nested list into numpy array. * WIP: add hifigan * WIP:update hifigan * change stft to use conv1d * add audio datasets * change batch_text_id, batch_spec, batch_wav to include valid lengths in the returned value * change wavenet to use on-the-fly prepeocessing * fix typos * resolve conflict * remove imports that are removed * remove files not included in this release * remove imports to deleted modules * move tacotron2_msp * clean code * fix argument order * fix argument name * clean code for data processing * WIP: add README * add more details to thr README, fix some preprocess scripts * add voice cloning notebook * add an optional to alter the loss and model structure of tacotron2, add an alternative config * add plot_multiple_attentions and update visualization code in transformer_tts * format code * remove tacotron2_msp * update tacotron2 from_pretrained, update setup.py * update tacotron2 * update tacotron_aishell3's README * add images for exampels/tacotron2_aishell3's README * update README for examples/ge2e * add STFT back * add extra_config keys into the default config of tacotron * fix typos and docs * update README and doc * update docstrings for tacotron * update doc * update README * add links to downlaod pretrained models * refine READMEs and clean code * add praatio into requirements for running the experiments * format code with pre-commit * simplify text processing code and update notebook
2021-05-13 17:49:50 +08:00
'numba',
'tqdm',
'llvmlite',
2020-02-26 21:03:51 +08:00
'matplotlib',
2021-08-27 18:42:08 +08:00
'visualdl==2.2.0',
2020-02-26 21:03:51 +08:00
'scipy',
'pandas',
'sox',
'soundfile~=0.10',
'g2p_en',
2020-12-03 18:42:36 +08:00
'yacs',
add ge2e and tacotron2_aishell3 example (#107) * hacky thing, add tone support for acoustic model * fix experiments for waveflow and wavenet, only write visual log in rank-0 * use emb add in tacotron2 * 1. remove space from numericalized representation; 2. fix decoder paddign mask's unsqueeze dim. * remove bn in postnet * refactoring code * add an option to normalize volume when loading audio. * add an embedding layer. * 1. change the default min value of LogMagnitude to 1e-5; 2. remove stop logit prediction from tacotron2 model. * WIP: baker * add ge2e * fix lstm speaker encoder * fix lstm speaker encoder * fix speaker encoder and add support for 2 more datasets * simplify visualization code * add a simple strategy to support multispeaker for tacotron. * add vctk example for refactored tacotron * fix indentation * fix class name * fix visualizer * fix root path * fix root path * fix root path * fix typos * fix bugs * fix text log extention name * add example for baker and aishell3 * update experiment and display * format code for tacotron_vctk, add plot_waveform to display * add new trainer * minor fix * add global condition support for tacotron2 * add gst layer * add 2 frontend * fix fmax for example/waveflow * update collate function, data loader not does not convert nested list into numpy array. * WIP: add hifigan * WIP:update hifigan * change stft to use conv1d * add audio datasets * change batch_text_id, batch_spec, batch_wav to include valid lengths in the returned value * change wavenet to use on-the-fly prepeocessing * fix typos * resolve conflict * remove imports that are removed * remove files not included in this release * remove imports to deleted modules * move tacotron2_msp * clean code * fix argument order * fix argument name * clean code for data processing * WIP: add README * add more details to thr README, fix some preprocess scripts * add voice cloning notebook * add an optional to alter the loss and model structure of tacotron2, add an alternative config * add plot_multiple_attentions and update visualization code in transformer_tts * format code * remove tacotron2_msp * update tacotron2 from_pretrained, update setup.py * update tacotron2 * update tacotron_aishell3's README * add images for exampels/tacotron2_aishell3's README * update README for examples/ge2e * add STFT back * add extra_config keys into the default config of tacotron * fix typos and docs * update README and doc * update docstrings for tacotron * update doc * update README * add links to downlaod pretrained models * refine READMEs and clean code * add praatio into requirements for running the experiments * format code with pre-commit * simplify text processing code and update notebook
2021-05-13 17:49:50 +08:00
'pypinyin',
'webrtcvad',
'g2pM',
2021-08-05 17:14:43 +08:00
'praatio~=4.1',
2021-06-17 00:18:13 +08:00
"h5py",
"timer",
'jsonlines',
2021-08-05 17:14:43 +08:00
'pyworld',
'typeguard',
'jieba',
"phkit",
2019-11-22 11:32:59 +08:00
],
2021-08-17 15:29:30 +08:00
extras_require={
'doc': ["sphinx", "sphinx-rtd-theme", "numpydoc"],
},
2019-11-22 11:32:59 +08:00
# Package info
2019-11-25 19:09:33 +08:00
packages=find_packages(exclude=('tests', 'tests.*')),
2020-12-20 13:15:07 +08:00
zip_safe=True,
classifiers=[
2020-12-19 18:55:42 +08:00
'Development Status :: 4 - Beta',
'Intended Audience :: Developers',
2020-12-20 14:21:36 +08:00
'Intended Audience :: Science/Research',
'Topic :: Scientific/Engineering :: Artificial Intelligence',
'License :: OSI Approved :: Apache Software License',
2020-12-19 18:55:42 +08:00
'Programming Language :: Python :: 3.6',
'Programming Language :: Python :: 3.7',
2020-12-20 13:15:07 +08:00
], )
2019-11-22 11:32:59 +08:00
2020-02-26 21:03:51 +08:00
setup(**setup_info)