tts_data_ch_preprocessing/pyproject.toml at main · i4Ds/tts_data_ch_preprocessing · 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
[project]
name = "tts_data_ch_preprocessing"
version = "0.1.0"
description = "End-to-end preprocessing pipeline for Swiss-German TTS data"
readme = "README.md"
requires-python = ">=3.11"
dependencies = [
    # Step 3a: German transcription
    "transformers>=4.40.0",
    "torch>=2.0.0",
    "torchaudio>=2.0.0",
    # Step 3b: Speech emotion recognition
    "torchaudio>=2.0.0",
    "numpy>=1.24.0",
    # Step 3c: Audio pattern recognition (PANNs/AudioSet)
    "panns-inference",
    "librosa>=0.10.0",
    # Step 2/4/5: General
    "pydub>=0.25.0",
    "numpy>=1.24.0",
    "tqdm>=4.65.0",
    "backoff>=2.2.0",
    "openai>=1.0.0",
    "onnxruntime>=1.18.0",
]

[project.optional-dependencies]
dev = [
    "pytest>=8.0.0",
]

[tool.setuptools]
packages = ["dialect", "vad_diarization"]
py-modules = ["ctc_alignment", "pipeline", "srt_formatter"]

[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"