-
Notifications
You must be signed in to change notification settings - Fork 12
Expand file tree
/
Copy pathsetup.py
More file actions
134 lines (131 loc) · 3.95 KB
/
setup.py
File metadata and controls
134 lines (131 loc) · 3.95 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
import os
from glob import glob
from setuptools import setup, find_packages
from pathlib import Path
# Utility function to read the README file.
# Used for the long_description. It's nice, because now 1) we have a top level
# README file and 2) it's easier to type in the README file than to put a raw
# string in below ...
def read(fname):
return open(os.path.join(os.path.dirname(__file__), fname), encoding='utf-8', errors='ignore').read()
with open(Path("./batchalign") / "version", 'r') as df:
VERSION_NUMBER, RELEASE_DATE, RELEASE_NOTES = df.readlines()[:3]
setup(
name = "batchalign",
author = "Brian MacWhinney, Houjun Liu",
author_email = "macw@cmu.edu, houjun@cmu.edu",
version = VERSION_NUMBER.strip(),
description = ("Python Speech Language Sample Analysis"),
packages=find_packages(),
long_description=read('README.md'),
entry_points = {
'console_scripts': ['batchalign=batchalign.cli.cli:batchalign'],
},
long_description_content_type='text/markdown',
install_requires=[
"pydantic>=2.4",
"platformdirs>=4.3.0",
"filelock>=3.0.0",
"nltk>=3.8",
"praatio>=6.0.0,<6.1.0",
"torch>=2.10.0",
"torchaudio>=2.10.0", # Only uses transforms/functional/pipelines (I/O via soundfile)
"soundfile>=0.12.0", # Audio I/O backend (replaces torchaudio.load/save/info)
# "pyAudioAnalysis",
# "hmmlearn==0.3.0",
# "eyed3",
"pydub",
# "imblearn",
"plotly>=5.3.0",
"transformers>=4.38.2",
"tokenizers>=0.14.1",
"numba>=0.61.0",
"numpy<=2.2",
"pycountry>=22.3",
"stanza[transformers]>=1.10.1",
"scipy~=1.11",
"rev_ai>=2.18.0",
"rich~=13.6",
"omegaconf",
"click~=8.1",
"matplotlib>=3.8.0,<4.0.0",
"pyfiglet==1.0.2",
"setuptools>=78.1.1",
"rich-click>=1.7.0",
"typing-extensions",
"num2words",
"tiktoken",
"blobfile",
"sentencepiece",
"googletrans",
"openai-whisper",
"llvmlite>=0.44.0",
"praat-parselmouth==0.4.6",
"opensmile>=2.5.0",
"pyannote.audio",
"onnxruntime",
"certifi>=2025.10.5"
],
extras_require={
'dev': [
'pytest',
'mypy',
'pyrefly',
'ty',
],
'train': [
'accelerate~=0.27',
],
'docs': [
'mkdocs-material',
'mkdocs-click'
],
# 'speaker': [
# "nemo-toolkit~=1.21.0",
# "omegaconf~=2.3.0",
# "pydub~=0.25.0",
# "braceexpand",
# "editdistance",
# "g2p_en",
# "ipywidgets",
# "jiwer",
# "kaldi-python-io",
# "kaldiio",
# "lhotse>=1.20.0",
# "librosa>=0.10.0",
# "marshmallow",
# "matplotlib",
# "packaging",
# "pyannote.core",
# "pyannote.metrics",
# "pydub",
# "pyloudnorm",
# "resampy",
# "ruamel.yaml",
# "scipy>=0.14",
# "soundfile",
# "sox",
# "texterrors",
# "hydra-core>1.3,<=1.3.2",
# "omegaconf<=2.3",
# "pytorch-lightning>=2.2.1",
# "torchmetrics>=0.11.0",
# "transformers>=4.36.0",
# "wandb",
# "webdataset>=0.2.86",
# "sentencepiece",
# "youtokentome",
# ]
},
include_package_data=True,
python_requires='>=3.11',
classifiers=[
"Development Status :: 3 - Alpha",
"Topic :: Utilities",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Programming Language :: Python :: 3.14",
]
)