forked from gaspardpetit/verbatim
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpyproject.toml
136 lines (121 loc) · 3.37 KB
/
pyproject.toml
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
135
[project]
name = "verbatim"
dynamic = ["version"]
description = "high quality multi-lingual speech to text"
readme = "README.md"
requires-python = ">=3.9,<3.12"
license = "MIT"
authors = [{ name = "Gaspard Petit", email = "[email protected]" }]
keywords = [
"speech-to-text",
"audio processing",
"multilingual",
"natural language processing",
"automatic speech recognition",
"ASR",
"text transcription",
"language support",
"machine learning",
"deep learning",
"NLP",
"linguistics",
"voice recognition",
"PyTorch",
"TensorFlow",
"audio analysis",
"speech analytics",
"spoken language processing",
"i18n",
"internationalization",
]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"Topic :: Multimedia :: Sound/Audio :: Speech",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Software Development :: Libraries :: Python Modules",
"Topic :: Text Processing :: Linguistic",
"Topic :: Multimedia :: Sound/Audio :: Analysis",
"License :: CC0 1.0 Universal (CC0 1.0) Public Domain Dedication",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
]
dependencies = [
"audio-separator>=0.18.0",
"av>=14.0.1",
"colorama>=0.4.6",
"dataclasses-json>=0.6.7",
"demucs>=4.0.1",
"faster-whisper>=1.1.1",
"langcodes>=3.5.0",
"numpy<=1.26.3",
"onnxruntime>=1.16.0",
"onnxruntime>=1.16.0 ; python_version > '3.9'",
"onnxruntime<1.20 ; python_version <= '3.9'", # see https://github.com/astral-sh/uv/issues/9425
"openai-whisper>=20240930",
"pyannote-audio[separation]>=3.3.2",
"pyannote-core>=5.0.0",
"pyaudio>=0.2.14",
"pydub>=0.25.1",
"python-docx>=1.1.2",
"silero-vad>=5.1.2",
"sounddevice>=0.5.1",
"soundfile>=0.13.0",
"speechbrain>=1.0.2",
"torch>=2.4.1",
"torchaudio>=2.4.1",
"wheel>=0.45.1",
"wtpsplit>=2.1.2",
"llvmlite==0.43.0",
"pillow==10.4.0",
"pywhispercpp>=1.3.0",
"mlx-whisper>=0.4.1 ; sys_platform == 'darwin'",
"word-levenshtein>=0.0.3",
"openai>=1.59.8",
]
[dependency-groups]
dev = [
"pylint>=3.3.3",
"pytest>=8.3.4",
"ruff>=0.8.6",
]
[project.optional-dependencies]
cuda_gpu = [
"onnxruntime-gpu>=1.16.0 ; python_version > '3.9'",
"onnxruntime-gpu<1.20 ; python_version <= '3.9'", # see https://github.com/astral-sh/uv/issues/9425
]
[project.urls]
Homepage = "https://github.com/gaspardpetit/verbatim"
[project.scripts]
verbatim = "verbatim.main:main"
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build]
include = ["verbatim/**/*"]
[tool.hatch.version]
path = "verbatim/__init__.py"
[tool.poetry]
version = "0.0.0"
[tool.poetry-dynamic-versioning]
enable = true
[tool.pyright]
venvPath = "."
venv = ".venv"
#[tool.uv.sources]
#torch = [
# { index = "pytorch-cu124", marker = "'cuda_gpu' in extra and sys_platform != 'darwin'" },
#]
#torchaudio = [
# { index = "pytorch-cu124", marker = "'cuda_gpu' in extra and sys_platform != 'darwin'" },
#]
[[tool.uv.index]]
name = "pytorch-cu124"
url = "https://download.pytorch.org/whl/cu124"
explicit = true
[tool.ruff]
line-length = 150
indent-width = 4