Mike Swanson
a1e0442d8b
- Audio processor CLI tool with 6-stage pipeline: transcribe (faster-whisper GPU), diarize (pyannote), detect segments (multi-signal classifier), remove commercials, split segments, analyze content (Ollama) - Post-show workflow doc for episode posts, forum threads, deep-dive blog posts - Training plan for using 579-episode archive for voice profiles and commercial detection - Successful test: 45min episode transcribed in 2:37 on RTX 5070 Ti - Sample transcript output from S7E30 (March 2015) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
26 lines
480 B
TOML
26 lines
480 B
TOML
[build-system]
|
|
requires = ["setuptools>=68.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "radio-processor"
|
|
version = "0.1.0"
|
|
description = "Audio processor for The Computer Guru Show"
|
|
requires-python = ">=3.11"
|
|
dependencies = [
|
|
"faster-whisper",
|
|
"pyannote.audio",
|
|
"pydub",
|
|
"librosa",
|
|
"scikit-learn",
|
|
"ollama",
|
|
"rich",
|
|
"pyyaml",
|
|
]
|
|
|
|
[project.scripts]
|
|
radio-process = "src.cli:main"
|
|
|
|
[tool.setuptools.packages.find]
|
|
include = ["src*"]
|