Hermes Agent
4590dc0fb9
Sermon-clean v0.2.0. Five new subcommands that round out the editor: - normalize (norm): Apply EBU R128 two-pass loudness normalization. Default -16 LUFS (podcast/YouTube). Configurable target LUFS, true peak, and loudness range. Output reports measured input loudness and applied gain offset. - silence-stats (ss): Quantitative summary of silence distribution — count, total/mean/median/longest silence, silence fraction, and silence runs per minute. Outputs JSON via --json. Useful for comparing recordings and picking the right threshold. - threshold-tune (tt): Auto-pick the silence threshold for the audio. Scans a set of candidate thresholds (default -25..-50), scores each against the target silence-runs-per-minute (default 4.0), picks the closest match. Shows the full scoring table. - denoise: Apply ffmpeg's afftdn filter for light FFT-based noise reduction. Configurable noise reduction dB (default 12) and noise floor dB (default -50). Output at 48kHz to match normalize. - batch: Run any of the subcommands across many files via glob. Output goes to --output-dir with --suffix (default '-fixed') and optional --extension override. Failures are collected, not raised — one bad file doesn't kill the whole batch. Implementation: - sermon_clean/processing.py: normalize_loudness + SilenceStats dataclass + silence_stats + threshold_tune. - sermon_clean/denoise.py: DenoiseResult + denoise. - sermon_clean/batch.py: run_batch + _expand_globs + _make_output_path. - sermon_clean/cli.py: 5 new cmd_* functions + 5 subparser registrations. Tests: - tests/test_processing.py (7 tests): silence-stats on silent vs loud, threshold-tune picks closest, normalize produces output + measures loud. - tests/test_denoise_batch.py (11 tests): denoise roundtrip, batch helpers (glob expansion, output naming), batch run with normalize + denoise, unknown subcommand raises, one-bad-file-in-batch continues. Total: 82/82 tests passing in 48s (was 64/64). Bumped version to 0.2.0. README updated: step-by-step workflow adds 1d-1g; subcommand table adds the 5 new commands; new 'Batch processing' section.
580 lines
26 KiB
Python
580 lines
26 KiB
Python
"""CLI for sermon-clean — the three-step audio editor.
|
|
|
|
Usage:
|
|
sermon-clean find sermon.ogg --silence-threshold -30 # shows silence gaps
|
|
sermon-clean cut sermon.ogg --segments segs.json --replacements rep/*.mp3 -o fixed.ogg
|
|
sermon-clean pipe sermon.ogg --bad "21:38-21:42, 1450.3-1453.1" \\
|
|
--replace "21:38-21:42:the actual sentence" \\
|
|
--replace "1450.3-1453.1:the corrected phrase"
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
from .engine import (
|
|
SermonClean,
|
|
detect_silence,
|
|
format_timestamp,
|
|
probe_duration,
|
|
)
|
|
|
|
USAGE = """sermon-clean — find bad segments, cut, paste replacements
|
|
|
|
Three-step workflow:
|
|
|
|
1. FIND: locate bad segments
|
|
- manual: --bad "MM:SS-MM:SS[, MM:SS-MM:SS, ...]"
|
|
- silence: --find-silence (prints gaps between speech)
|
|
- explicit JSON file: --segments-file segs.json
|
|
|
|
2. CUT: Trim the original audio around the bad windows.
|
|
(happens automatically when you run 'paste' or 'pipe')
|
|
|
|
3. PASTE: Render replacement clips via ElevenLabs, or supply pre-rendered ones.
|
|
- ElevenLabs: --render-elevenlabs TEXT (one per --bad segment)
|
|
- Pre-rendered: --replacements rep/*.mp3 (one per --bad segment)
|
|
|
|
'pipe' runs all three in one command.
|
|
"""
|
|
|
|
|
|
def _parse_bad_spec(spec: str) -> list[tuple[float, float, str]]:
|
|
"""Parse 'MM:SS-MM:SS:TEXT, MM:SS-MM:SS:TEXT' into [(start, end, text), ...]."""
|
|
from .engine import parse_timestamp
|
|
out = []
|
|
for item in spec.split(","):
|
|
item = item.strip()
|
|
if not item:
|
|
continue
|
|
# Find the timestamp range via regex
|
|
if "-" not in item:
|
|
raise ValueError(f"bad segment spec missing '-': {item!r}")
|
|
# Find the colon in the second timestamp that separates MM:SS from the text
|
|
# Strategy: first occurrence of "-" splits range; rest is text
|
|
# We need to NOT split on the "-" inside the timestamps (none, but be safe)
|
|
# Actually timestamps use ":" only, not "-", so first "-" is safe.
|
|
dash_idx = item.index("-")
|
|
start_str = item[:dash_idx]
|
|
rest = item[dash_idx + 1:]
|
|
# The rest is either "MM:SS" or "MM:SS:TEXT"
|
|
# Find the second timestamp by parsing prefix until we have valid MM:SS
|
|
# Try 4-char prefix (MM:SS) then 7-char prefix (HH:MM:SS)
|
|
if ":" in rest:
|
|
# Find the colon after the minutes field
|
|
# First timestamp is MM:SS or HH:MM:SS
|
|
# Second timestamp ends at either ":" or end
|
|
# Try parsing increasing prefix lengths
|
|
for try_len in range(len(rest), 0, -1):
|
|
candidate = rest[:try_len]
|
|
try:
|
|
parse_timestamp(candidate)
|
|
start = parse_timestamp(start_str)
|
|
end = parse_timestamp(candidate)
|
|
text = rest[try_len + 1:].lstrip() if try_len < len(rest) - 1 else ""
|
|
# If there's a leading ":" after the timestamp, strip it
|
|
if text.startswith(":"):
|
|
text = text[1:].lstrip()
|
|
out.append((start, end, text))
|
|
break
|
|
except ValueError:
|
|
continue
|
|
else:
|
|
raise ValueError(f"could not parse second timestamp in: {item!r}")
|
|
else:
|
|
# Just "MM:SS" with no text
|
|
start = parse_timestamp(start_str)
|
|
end = parse_timestamp(rest)
|
|
out.append((start, end, ""))
|
|
return out
|
|
|
|
|
|
def cmd_find(args: argparse.Namespace) -> int:
|
|
"""Print metadata + (optional) silence gaps + (optional) segments from a JSON file."""
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
sc = SermonClean(audio)
|
|
print(f"file: {audio}")
|
|
print(f"duration: {format_timestamp(sc.duration)} ({sc.duration:.3f}s)")
|
|
print(f"codec: {sc.codec['codec_name']} / {sc.codec['sample_rate']}Hz / {sc.codec['channels']}ch")
|
|
if args.silence_threshold is not None:
|
|
gaps = detect_silence(audio, noise_db=args.silence_threshold, min_duration=args.silence_min_duration)
|
|
print(f"\nsilence gaps (noise<{args.silence_threshold}dB, dur>={args.silence_min_duration}s):")
|
|
for a, b in gaps:
|
|
print(f" {format_timestamp(a)} -> {format_timestamp(b)} ({b-a:.2f}s)")
|
|
if args.segments_file:
|
|
n = sc.load_segments_from_json(Path(args.segments_file))
|
|
print(f"\nloaded {n} segments from {args.segments_file}:")
|
|
for s in sc.segments:
|
|
print(f" {format_timestamp(s.start)} -> {format_timestamp(s.end)} ({s.duration:.2f}s) reason={s.reason!r}")
|
|
return 0
|
|
|
|
|
|
def cmd_cut(args: argparse.Namespace) -> int:
|
|
"""Just trim the original around the bad windows (no splice)."""
|
|
audio = Path(args.audio)
|
|
sc = SermonClean(audio)
|
|
if args.segments_file:
|
|
sc.load_segments_from_json(Path(args.segments_file))
|
|
elif args.bad:
|
|
for start, end, text in _parse_bad_spec(args.bad):
|
|
sc.add_segment(start, end, replacement_text=text)
|
|
else:
|
|
print("error: provide --bad or --segments-file", file=sys.stderr)
|
|
return 1
|
|
out = sc.trim_segments()
|
|
print(f"trimmed into {len(out)} segments in {sc.workdir}")
|
|
for p in out:
|
|
print(f" {p} ({probe_duration(p):.2f}s)")
|
|
return 0
|
|
|
|
|
|
def cmd_paste(args: argparse.Namespace) -> int:
|
|
"""Take pre-rendered replacement clips and splice them in."""
|
|
audio = Path(args.audio)
|
|
sc = SermonClean(audio)
|
|
if args.segments_file:
|
|
sc.load_segments_from_json(Path(args.segments_file))
|
|
elif args.bad:
|
|
for start, end, text in _parse_bad_spec(args.bad):
|
|
sc.add_segment(start, end, replacement_text=text)
|
|
else:
|
|
print("error: provide --bad or --segments-file", file=sys.stderr)
|
|
return 1
|
|
if not args.replacements:
|
|
print("error: provide --replacements (one per bad segment, in order)", file=sys.stderr)
|
|
return 1
|
|
import glob
|
|
paths = []
|
|
for pat in args.replacements:
|
|
paths.extend(sorted(glob.glob(pat)))
|
|
if len(paths) != len(sc.segments):
|
|
print(f"error: {len(paths)} replacement files but {len(sc.segments)} bad segments", file=sys.stderr)
|
|
return 1
|
|
output = Path(args.output) if args.output else audio.with_name(f"{audio.stem}-fixed{audio.suffix}")
|
|
result = sc.clean([Path(p) for p in paths], output)
|
|
print(f"output: {result.output_path}")
|
|
print(f"duration: {format_timestamp(result.duration_seconds)} (was {format_timestamp(result.original_duration)})")
|
|
print(f"duration check: {result.duration_check()}")
|
|
return 0
|
|
|
|
|
|
def cmd_silence_index(args: argparse.Namespace) -> int:
|
|
"""Print a tabular index of silence runs with timestamps."""
|
|
from .waveform import render_silence_index
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
print(render_silence_index(
|
|
audio,
|
|
threshold_db=args.silence_threshold,
|
|
min_duration=args.silence_min_duration,
|
|
))
|
|
return 0
|
|
|
|
|
|
def cmd_multiband(args: argparse.Namespace) -> int:
|
|
"""Print a multi-band ASCII waveform. Each row is N seconds labeled."""
|
|
from .waveform import render_multiband_waveform
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
print(render_multiband_waveform(
|
|
audio,
|
|
width=args.width,
|
|
band_seconds=args.band_seconds,
|
|
))
|
|
return 0
|
|
|
|
|
|
def cmd_normalize(args: argparse.Namespace) -> int:
|
|
"""Apply EBU R128 loudness normalization."""
|
|
from .processing import normalize_loudness
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
output = Path(args.output) if args.output else audio.with_name(f"{audio.stem}-normalized{audio.suffix}")
|
|
result = normalize_loudness(
|
|
audio, output,
|
|
target_lufs=args.target_lufs,
|
|
true_peak_db=args.true_peak,
|
|
loudness_range_lu=args.loudness_range,
|
|
)
|
|
print(f"normalized: {result['output_path']}")
|
|
print(f"target: {result['target_lufs']} LUFS, true peak {result['true_peak_db']}dB")
|
|
print(f"measured input loudness: {result['measured_input_i']} LUFS")
|
|
print(f"applied gain offset: {result['applied_offset']} dB")
|
|
return 0
|
|
|
|
|
|
def cmd_silence_stats(args: argparse.Namespace) -> int:
|
|
"""Quantitative summary of silence distribution (count, mean, longest)."""
|
|
from .processing import silence_stats
|
|
import json
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
stats = silence_stats(
|
|
audio,
|
|
threshold_db=args.silence_threshold,
|
|
min_duration_seconds=args.silence_min_duration,
|
|
)
|
|
if args.json:
|
|
print(json.dumps(stats.to_dict(), indent=2))
|
|
return 0
|
|
# Human-readable summary
|
|
print(f"file: {stats.audio_path}")
|
|
print(f"duration: {stats.duration_seconds:.2f}s")
|
|
print(f"threshold: {stats.threshold_db}dB, min duration: {stats.min_duration_seconds}s")
|
|
print()
|
|
print(f"silence runs: {stats.n_silence_runs}")
|
|
print(f"total silence: {stats.total_silence_seconds:.2f}s ({stats.silence_fraction*100:.1f}% of audio)")
|
|
print(f"mean silence: {stats.mean_silence_seconds:.2f}s")
|
|
print(f"median silence: {stats.median_silence_seconds:.2f}s")
|
|
print(f"longest silence: {stats.longest_silence_seconds:.2f}s "
|
|
f"@ {stats.longest_silence_range[0]:.1f}-{stats.longest_silence_range[1]:.1f}s")
|
|
print(f"silence density: {stats.silence_per_minute:.2f} runs/min")
|
|
return 0
|
|
|
|
|
|
def cmd_threshold_tune(args: argparse.Namespace) -> int:
|
|
"""Auto-pick the silence threshold for this audio based on expected pause density."""
|
|
from .processing import threshold_tune
|
|
import json
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
candidates = [float(x) for x in args.candidates.split(",")]
|
|
result = threshold_tune(
|
|
audio,
|
|
candidates=candidates,
|
|
target_silence_per_minute=args.target_spm,
|
|
target_min_duration=args.min_duration,
|
|
)
|
|
if args.json:
|
|
print(json.dumps(result, indent=2))
|
|
return 0
|
|
print(f"target: {result['target_silence_per_minute']:.1f} silence runs/min")
|
|
print(f"picked threshold: {result['picked_threshold_db']}dB "
|
|
f"(gives {result['picked_silence_per_minute']:.2f} runs/min)")
|
|
print()
|
|
print(f"{'threshold_dB':>12} {'runs':>6} {'runs/min':>10} {'distance':>10}")
|
|
for row in result["candidates"]:
|
|
marker = " ← picked" if row["threshold_db"] == result["picked_threshold_db"] else ""
|
|
print(f"{row['threshold_db']:>12.0f} {row['n_runs']:>6} {row['silence_per_minute']:>10.2f} "
|
|
f"{row['distance_from_target']:>10.2f}{marker}")
|
|
return 0
|
|
|
|
|
|
def cmd_denoise(args: argparse.Namespace) -> int:
|
|
"""Apply light FFT-based noise reduction (good for tape hiss, mic preamp noise)."""
|
|
from .denoise import denoise
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
output = Path(args.output) if args.output else audio.with_name(f"{audio.stem}-denoised{audio.suffix}")
|
|
result = denoise(
|
|
audio, output,
|
|
noise_reduction_db=args.noise_reduction,
|
|
noise_floor_db=args.noise_floor,
|
|
)
|
|
print(f"denoised: {result.output_path}")
|
|
print(f"noise reduction: {result.noise_reduction_db}dB (assumed floor: {result.noise_floor_db}dB)")
|
|
return 0
|
|
|
|
|
|
def cmd_batch(args: argparse.Namespace) -> int:
|
|
"""Run a sermon-clean subcommand across many files."""
|
|
from .batch import run_batch
|
|
output_dir = Path(args.output_dir)
|
|
result = run_batch(
|
|
args.subcommand,
|
|
[Path(p) for p in args.sources],
|
|
output_dir,
|
|
output_suffix=args.suffix or "-fixed",
|
|
output_extension=args.extension,
|
|
# Don't forward --suffix or --extension to the subcommand — they're
|
|
# batch-only knobs that control output naming, not subcommand args.
|
|
extra_args=[],
|
|
)
|
|
print(result.summary())
|
|
return 0 if result.n_failed == 0 else 1
|
|
|
|
|
|
def cmd_slices(args: argparse.Namespace) -> int:
|
|
"""Extract overlapping audio slices for manual review.
|
|
|
|
Useful when you don't have exact timestamps and want to scrub through
|
|
the audio in a media player, marking bad segments as you go.
|
|
"""
|
|
from .slices import extract_slices
|
|
audio = Path(args.audio)
|
|
out = Path(args.output_dir)
|
|
paths = extract_slices(
|
|
audio, out,
|
|
slice_seconds=args.slice_seconds,
|
|
overlap_seconds=args.overlap_seconds,
|
|
)
|
|
print(f"extracted {len(paths)} slices into {out}")
|
|
for p in paths:
|
|
print(f" {p.name}")
|
|
print()
|
|
print(f"play them in any media player, then mark bad-segment start/end times")
|
|
print(f"in your audio player's display, then build a segments JSON and run:")
|
|
print(f" sermon-clean auto {audio} --bad-words ...")
|
|
return 0
|
|
|
|
|
|
def cmd_scan(args: argparse.Namespace) -> int:
|
|
"""Print an ASCII waveform + silence marks for the audio. No whisper, fast."""
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
from .waveform import render_ascii_waveform, render_silence_marks
|
|
print(f"=== waveform: {audio} ===")
|
|
print(render_ascii_waveform(audio, width=args.width))
|
|
print()
|
|
print(f"=== silence runs (noise<{args.silence_threshold}dB, dur>={args.silence_min_duration}s) ===")
|
|
print(render_silence_marks(
|
|
audio,
|
|
threshold_db=args.silence_threshold,
|
|
min_duration_seconds=args.silence_min_duration,
|
|
width=args.width,
|
|
))
|
|
return 0
|
|
|
|
|
|
def cmd_auto(args: argparse.Namespace) -> int:
|
|
"""Transcribe audio with faster-whisper + suggest bad-word segments."""
|
|
audio = Path(args.audio)
|
|
if not audio.exists():
|
|
print(f"error: {audio} not found", file=sys.stderr)
|
|
return 1
|
|
try:
|
|
from .transcribe import (
|
|
find_bad_words,
|
|
suggest_replacements,
|
|
export_to_segments_json,
|
|
)
|
|
except ImportError as e:
|
|
print(f"error: --auto requires the [auto] extra: {e}", file=sys.stderr)
|
|
print("install with: pip install 'sermon-clean[auto]'", file=sys.stderr)
|
|
return 1
|
|
|
|
bad_words = [w.strip() for w in args.bad_words.split(",") if w.strip()]
|
|
print(f"transcribing {audio} with model={args.model}, scanning for: {bad_words}...")
|
|
hits = find_bad_words(
|
|
audio,
|
|
bad_words,
|
|
model_name=args.model,
|
|
confidence_threshold=args.confidence_threshold,
|
|
)
|
|
print(f"found {len(hits)} candidate bad-word hits")
|
|
if not hits:
|
|
print("no bad words detected — nothing to write")
|
|
return 0
|
|
|
|
# Get transcript context for replacement suggestions
|
|
from .transcribe import transcribe
|
|
words = transcribe(audio, model_name=args.model)
|
|
hits = suggest_replacements(hits, transcript_context=words, max_window=args.context_window)
|
|
segs = export_to_segments_json(hits, include_suggested_only=args.include_suggested_only)
|
|
|
|
out_path = Path(args.output)
|
|
out_path.write_text(json.dumps(segs, indent=2))
|
|
print(f"wrote {len(segs)} segments to {out_path}")
|
|
print("\nreview and edit the JSON before running 'paste' or 'pipe':")
|
|
print(f" sermon-clean paste {audio} --segments-file {out_path} --replacements 'replacements/*.mp3'")
|
|
return 0
|
|
|
|
|
|
def cmd_pipe(args: argparse.Namespace) -> int:
|
|
"""Cut + paste in one step. Use ElevenLabs to render replacements if --elevenlabs-text given."""
|
|
audio = Path(args.audio)
|
|
sc = SermonClean(audio)
|
|
if args.segments_file:
|
|
sc.load_segments_from_json(Path(args.segments_file))
|
|
elif args.bad:
|
|
for start, end, text in _parse_bad_spec(args.bad):
|
|
sc.add_segment(start, end, replacement_text=text)
|
|
else:
|
|
print("error: provide --bad or --segments-file", file=sys.stderr)
|
|
return 1
|
|
if args.elevenlabs_text:
|
|
# Lazy import so the core module doesn't depend on ElevenLabs
|
|
try:
|
|
from .elevenlabs import render_replacements
|
|
except ImportError:
|
|
print("error: elevenlabs rendering requires `pip install requests`", file=sys.stderr)
|
|
return 1
|
|
reps = render_replacements(sc.segments, voice_id=args.voice_id, api_key=args.elevenlabs_key)
|
|
elif args.replacements:
|
|
import glob
|
|
paths = []
|
|
for pat in args.replacements:
|
|
paths.extend(sorted(glob.glob(pat)))
|
|
reps = [Path(p) for p in paths]
|
|
else:
|
|
print("error: provide --replacements OR --elevenlabs-text", file=sys.stderr)
|
|
return 1
|
|
if len(reps) != len(sc.segments):
|
|
print(f"error: {len(reps)} replacements vs {len(sc.segments)} segments", file=sys.stderr)
|
|
return 1
|
|
output = Path(args.output) if args.output else audio.with_name(f"{audio.stem}-fixed{audio.suffix}")
|
|
result = sc.clean(reps, output)
|
|
print(f"output: {result.output_path}")
|
|
print(f"duration: {format_timestamp(result.duration_seconds)} (was {format_timestamp(result.original_duration)})")
|
|
print(f"duration check: {result.duration_check()}")
|
|
return 0
|
|
|
|
|
|
def main(argv: list[str] | None = None) -> int:
|
|
parser = argparse.ArgumentParser(
|
|
prog="sermon-clean",
|
|
description=USAGE,
|
|
formatter_class=argparse.RawDescriptionHelpFormatter,
|
|
)
|
|
sub = parser.add_subparsers(dest="cmd", required=True)
|
|
|
|
# find
|
|
p_find = sub.add_parser("find", help="Show audio metadata; optionally find silence gaps and load segments")
|
|
p_find.add_argument("audio")
|
|
p_find.add_argument("--silence-threshold", type=float, default=None, help="noise_db for silencedetect (e.g. -30)")
|
|
p_find.add_argument("--silence-min-duration", type=float, default=0.5, help="minimum silence in seconds")
|
|
p_find.add_argument("--segments-file", help="JSON file with bad segments")
|
|
p_find.set_defaults(func=cmd_find)
|
|
|
|
# cut
|
|
p_cut = sub.add_parser("cut", help="Trim the original audio around bad windows (no splice)")
|
|
p_cut.add_argument("audio")
|
|
p_cut.add_argument("--segments-file")
|
|
p_cut.add_argument("--bad", help='comma-separated MM:SS-MM:SS[:TEXT] windows')
|
|
p_cut.set_defaults(func=cmd_cut)
|
|
|
|
# paste
|
|
p_paste = sub.add_parser("paste", help="Splice pre-rendered replacement clips into a trimmed original")
|
|
p_paste.add_argument("audio")
|
|
p_paste.add_argument("--segments-file")
|
|
p_paste.add_argument("--bad")
|
|
p_paste.add_argument("-o", "--output")
|
|
p_paste.add_argument("--replacements", nargs="+", help="glob(s) for replacement MP3s in order")
|
|
p_paste.set_defaults(func=cmd_paste)
|
|
|
|
# silence-index (tabular list of silence runs with timestamps)
|
|
p_si = sub.add_parser("silence-index", aliases=["si"], help="Tabular index of silence runs with timestamps")
|
|
p_si.add_argument("audio")
|
|
p_si.add_argument("--silence-threshold", type=float, default=-35.0, help="noise_db threshold")
|
|
p_si.add_argument("--silence-min-duration", type=float, default=0.3, help="minimum silence in seconds")
|
|
p_si.set_defaults(func=cmd_silence_index)
|
|
|
|
# multiband (multi-row ASCII waveform with band labels)
|
|
p_mb = sub.add_parser("multiband", aliases=["mb"], help="Multi-band ASCII waveform with band-start labels")
|
|
p_mb.add_argument("audio")
|
|
p_mb.add_argument("--width", type=int, default=60, help="waveform width in columns per band")
|
|
p_mb.add_argument("--band-seconds", type=float, default=60.0, help="seconds of audio per band (one row)")
|
|
p_mb.set_defaults(func=cmd_multiband)
|
|
|
|
# slices (extract overlapping audio chunks for manual review)
|
|
p_slices = sub.add_parser("slices", help="Extract overlapping audio slices for manual review")
|
|
p_slices.add_argument("audio")
|
|
p_slices.add_argument("--output-dir", default="./slices", help="directory to write slices")
|
|
p_slices.add_argument("--slice-seconds", type=float, default=5.0, help="length of each slice")
|
|
p_slices.add_argument("--overlap-seconds", type=float, default=1.0, help="overlap between adjacent slices")
|
|
p_slices.set_defaults(func=cmd_slices)
|
|
|
|
# normalize (EBU R128 loudness normalization)
|
|
p_norm = sub.add_parser("normalize", aliases=["norm"], help="Apply EBU R128 loudness normalization")
|
|
p_norm.add_argument("audio")
|
|
p_norm.add_argument("-o", "--output", help="output file (default: <stem>-normalized<ext>)")
|
|
p_norm.add_argument("--target-lufs", type=float, default=-16.0, help="target integrated loudness (LUFS, default -16 for podcast/YouTube)")
|
|
p_norm.add_argument("--true-peak", type=float, default=-1.5, help="true peak ceiling in dB (default -1.5)")
|
|
p_norm.add_argument("--loudness-range", type=float, default=11.0, help="loudness range target in LU (default 11)")
|
|
p_norm.set_defaults(func=cmd_normalize)
|
|
|
|
# silence-stats (quantitative summary of silence distribution)
|
|
p_ss = sub.add_parser("silence-stats", aliases=["ss"], help="Quantitative summary of silence distribution")
|
|
p_ss.add_argument("audio")
|
|
p_ss.add_argument("--silence-threshold", type=float, default=-35.0, help="noise_db threshold")
|
|
p_ss.add_argument("--silence-min-duration", type=float, default=0.3, help="minimum silence duration in seconds")
|
|
p_ss.add_argument("--json", action="store_true", help="output JSON instead of human-readable")
|
|
p_ss.set_defaults(func=cmd_silence_stats)
|
|
|
|
# threshold-tune (auto-pick silence threshold for this audio)
|
|
p_tt = sub.add_parser("threshold-tune", aliases=["tt"], help="Auto-pick the silence threshold based on expected pause density")
|
|
p_tt.add_argument("audio")
|
|
p_tt.add_argument("--candidates", default="-25,-30,-35,-40,-45,-50",
|
|
help="comma-separated threshold candidates in dB (default: -25,-30,-35,-40,-45,-50)")
|
|
p_tt.add_argument("--target-spm", type=float, default=4.0,
|
|
help="target silence runs per minute (default 4.0 — typical sermon pause rate)")
|
|
p_tt.add_argument("--min-duration", type=float, default=0.3,
|
|
help="minimum silence duration in seconds")
|
|
p_tt.add_argument("--json", action="store_true", help="output JSON instead of human-readable")
|
|
p_tt.set_defaults(func=cmd_threshold_tune)
|
|
|
|
# denoise (light FFT-based noise reduction)
|
|
p_dn = sub.add_parser("denoise", help="Apply light FFT-based noise reduction (afftdn)")
|
|
p_dn.add_argument("audio")
|
|
p_dn.add_argument("-o", "--output", help="output file (default: <stem>-denoised<ext>)")
|
|
p_dn.add_argument("--noise-reduction", type=float, default=12.0, help="noise attenuation in dB (default 12; higher = more aggressive)")
|
|
p_dn.add_argument("--noise-floor", type=float, default=-50.0, help="expected noise floor in dB (default -50)")
|
|
p_dn.set_defaults(func=cmd_denoise)
|
|
|
|
# batch (run any subcommand across many files)
|
|
p_batch = sub.add_parser("batch", help="Run a sermon-clean subcommand across many files")
|
|
p_batch.add_argument("subcommand", help="which sermon-clean subcommand to run (normalize, scan, etc.)")
|
|
p_batch.add_argument("sources", nargs="+", help="input files or glob patterns (e.g. 'sermons/*.ogg')")
|
|
p_batch.add_argument("--output-dir", required=True, help="directory to write outputs")
|
|
p_batch.add_argument("--suffix", default="-fixed", help="filename suffix for outputs (default '-fixed')")
|
|
p_batch.add_argument("--extension", help="extension override (e.g. '.wav'); defaults to input extension")
|
|
p_batch.set_defaults(func=cmd_batch)
|
|
|
|
# scan (ASCII waveform + silence marks, no whisper)
|
|
p_scan = sub.add_parser("scan", help="Print an ASCII waveform + silence marks for the audio")
|
|
p_scan.add_argument("audio")
|
|
p_scan.add_argument("--width", type=int, default=80, help="waveform width in columns")
|
|
p_scan.add_argument("--silence-threshold", type=float, default=-40.0, help="noise_db for silence detection")
|
|
p_scan.add_argument("--silence-min-duration", type=float, default=0.5, help="minimum silence duration in seconds")
|
|
p_scan.set_defaults(func=cmd_scan)
|
|
|
|
# auto (find bad words via faster-whisper)
|
|
p_auto = sub.add_parser("auto", help="Transcribe audio + flag bad words, write a candidate segments JSON")
|
|
p_auto.add_argument("audio")
|
|
p_auto.add_argument("--bad-words", required=True, help="comma-separated list of bad words to find (e.g. 'fuck,shit,damn')")
|
|
p_auto.add_argument("--model", default="tiny.en", help="whisper model name (tiny.en, base.en, small.en, ...)")
|
|
p_auto.add_argument("--output", "-o", required=True, help="output JSON file for the suggested segments")
|
|
p_auto.add_argument("--context-window", type=float, default=3.0, help="seconds before/after to look for context words")
|
|
p_auto.add_argument("--confidence-threshold", type=float, default=0.30, help="minimum word probability (whisper)")
|
|
p_auto.add_argument("--include-suggested-only", action="store_true", default=True, help="skip matches with no suggested replacement")
|
|
p_auto.set_defaults(func=cmd_auto)
|
|
|
|
# pipe (all in one)
|
|
p_pipe = sub.add_parser("pipe", help="Run cut + paste in one command")
|
|
p_pipe.add_argument("audio")
|
|
p_pipe.add_argument("--segments-file")
|
|
p_pipe.add_argument("--bad")
|
|
p_pipe.add_argument("-o", "--output")
|
|
p_pipe.add_argument("--replacements", nargs="+")
|
|
p_pipe.add_argument("--elevenlabs-text", action="store_true", help="use the --bad TEXT as ElevenLabs render input")
|
|
p_pipe.add_argument("--voice-id", help="ElevenLabs voice ID (or set ELEVENLABS_VOICE_ID)")
|
|
p_pipe.add_argument("--elevenlabs-key", help="ElevenLabs API key (or set ELEVENLABS_API_KEY)")
|
|
p_pipe.set_defaults(func=cmd_pipe)
|
|
|
|
args = parser.parse_args(argv)
|
|
return args.func(args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|