- 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>
58 lines
1.3 KiB
YAML
58 lines
1.3 KiB
YAML
show:
|
|
name: "The Computer Guru Show"
|
|
host: "Mike Swanson"
|
|
typical_duration_minutes: 120
|
|
segment_count: 6
|
|
has_commercials: true
|
|
|
|
audio:
|
|
whisper_model: "large-v3"
|
|
whisper_language: "en"
|
|
output_format: "mp3"
|
|
output_bitrate: "192k"
|
|
normalize: true
|
|
crossfade_ms: 500
|
|
|
|
segment_detection:
|
|
fingerprint_db: "element-library/fingerprints.db"
|
|
fingerprint_match_threshold: 0.85
|
|
|
|
discover_unknown_elements: true
|
|
min_element_duration_s: 1.0
|
|
max_element_duration_s: 30.0
|
|
cluster_similarity_threshold: 0.90
|
|
min_cluster_occurrences: 3
|
|
|
|
min_break_duration_s: 30
|
|
max_break_duration_s: 300
|
|
silence_threshold_db: -40
|
|
confidence_threshold: 0.70
|
|
|
|
weights:
|
|
fingerprint_match: 0.30
|
|
speaker_identity: 0.25
|
|
audio_characteristics: 0.20
|
|
break_pattern: 0.15
|
|
structural_heuristic: 0.10
|
|
|
|
diarization:
|
|
min_speakers: 1
|
|
max_speakers: 6
|
|
voice_profiles_dir: "voice-profiles/"
|
|
host_match_threshold: 0.75
|
|
|
|
llm:
|
|
model: "qwen3:14b"
|
|
ollama_host: "http://localhost:11434"
|
|
|
|
paths:
|
|
episodes_dir: "episodes/"
|
|
voice_profiles: "voice-profiles/"
|
|
element_library: "element-library/"
|
|
output_dir: "processed/"
|
|
|
|
archive:
|
|
server: "172.16.3.10"
|
|
path: "/home/gurushow/public_html/archive/"
|
|
elements_path: "/home/gurushow/public_html/archive/Radio/Elements/"
|