mlx-audio/pyproject.toml at main · OpenMOSS/mlx-audio · GitHub

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
136
137
138
139
140
141
142
[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "mlx-audio"
dynamic = ["version"]
description = "MLX-Audio is a package for inference of text-to-speech (TTS) and speech-to-speech (STS) models locally on your Mac using MLX"
readme = "README.md"
license = "MIT"
authors = [
    {name = "Prince Canuma", email = "prince.gdt@gmail.com"}
]
classifiers = [
    "Programming Language :: Python :: 3",
    "Operating System :: OS Independent",
]
requires-python = ">=3.10"

# Core dependencies
dependencies = [
    "mlx>=0.25.2",
    "numpy>=1.26.4",
    "huggingface_hub>=1.0",
    "transformers>=5.0.0",
    "mlx-lm==0.31.1",
    "tqdm>=4.67.1",
    "sounddevice==0.5.3",
    "miniaudio>=1.61",
    "pyloudnorm>=0.2.0",
    "numba>=0.60.0", # Required by librosa
    "librosa==0.11.0",
    "protobuf>=6.33.5",
]

[project.optional-dependencies]
# STT dependencies
stt = [
    "tiktoken>=0.9.0",
    "mistral-common[audio]",
]

# TTS dependencies
tts = [
    "misaki>=0.9.4",
    "num2words>=0.5.14",
    "spacy>=3.8.4",
    "phonemizer-fork>=3.3.2",
    "espeakng-loader>=0.2.4",
    "sentencepiece>=0.2.0",
]

# Server dependencies
server = [
    "fastapi>=0.95.0",
    "uvicorn>=0.22.0",
    "python-multipart>=0.0.22"
]

# STS (Speech-to-Speech) requires both STT and TTS + additional deps
sts = [
    "tiktoken>=0.9.0",
    "mistral-common[audio]",

    "misaki>=0.9.4",
    "num2words>=0.5.14",
    "spacy>=3.8.4",
    "phonemizer-fork>=3.3.2",
    "espeakng-loader>=0.2.4",
    "sentencepiece>=0.2.0",

    "webrtcvad>=2.0.10",
    "setuptools<81", # pinned because >=81 drops pkg_resources which breaks webrtcvad
]

# Full installation (all features)
all = [
    "tiktoken>=0.9.0",
    "mistral-common[audio]",

    "misaki>=0.9.4",
    "num2words>=0.5.14",
    "spacy>=3.8.4",
    "phonemizer-fork>=3.3.2",
    "espeakng-loader>=0.2.4",
    "sentencepiece>=0.2.0",

    "fastapi>=0.95.0",
    "uvicorn>=0.22.0",

    "webrtcvad>=2.0.10",
    "setuptools<81", # pinned because >=81 drops pkg_resources which breaks webrtcvad
]

# Development dependencies
dev = [
    "pytest>=7.0.0",
    "pytest-asyncio>=1.0.0",
    "black>=24.2.0",
    "isort>=5.13.2",
    "pre-commit>=3.7.0",
]

[project.scripts]
"mlx_audio.convert" = "mlx_audio.convert:main"
"mlx_audio.stt.generate" = "mlx_audio.stt.generate:main"
"mlx_audio.tts.generate" = "mlx_audio.tts.generate:main"
"mlx_audio.server" = "mlx_audio.server:main"
"mlx_audio.sts.generate" = "mlx_audio.sts.generate:main"

[project.urls]
Homepage = "https://github.com/Blaizzy/mlx-audio"
Repository = "https://github.com/Blaizzy/mlx-audio"

[tool.poetry]
version = "0.0.0"

[tool.setuptools.dynamic]
version = {attr = "mlx_audio.version.__version__"}

[tool.setuptools]
include-package-data = true

[tool.setuptools.packages.find]
where = ["."]
include = ["mlx_audio", "mlx_audio.*"]

[tool.setuptools.package-data]
mlx_audio = [
    "tts/*.html",
    "tts/*.js",
    "tts/*.css",
    "tts/**/*.json",
    "tts/static/**/*",
]

[tool.black]
line-length = 88
target-version = ["py310"]

[tool.isort]
profile = "black"