v5: refactor into modular stream_tools desktop app

Same inaSpeechSegmenter engine split into reusable core/ (fftools, segmenter, exporters) + utils/ and a CustomTkinter multi-tab UI. Adds JSON and ffmpeg-script export. Extracted from the stream_tools app.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

core/segmenter.py

@@ -0,0 +1,118 @@
+"""
+Singing segment detection via inaSpeechSegmenter.
+
+Pipeline:
+  1. Run inaSpeechSegmenter to classify speech/music/noise
+  2. Filter for 'music' segments (singing voice is classified as music)
+  3. Merge nearby segments, apply padding, filter by minimum duration
+"""
+
+import time
+from utils.formats import format_timecode
+
+
+def check_segmenter_available() -> tuple[bool, str]:
+    """Check if inaSpeechSegmenter is installed."""
+    try:
+        from inaSpeechSegmenter import Segmenter  # noqa: F401
+        return True, ""
+    except ImportError:
+        return False, (
+            "inaSpeechSegmenter is not installed.\n\n"
+            "Install it with:\n"
+            "  pip install inaSpeechSegmenter\n\n"
+            "You also need TensorFlow:\n"
+            "  pip install tensorflow[and-cuda]   (GPU)\n"
+            "  pip install tensorflow              (CPU)"
+        )
+
+
+def run_segmentation(wav_path: str, progress_cb=None) -> list:
+    """
+    Run inaSpeechSegmenter on audio file.
+    Returns list of (label, start_sec, end_sec) tuples.
+    Labels: 'music', 'speech', 'noise', 'noEnergy'
+    """
+    from inaSpeechSegmenter import Segmenter
+
+    if progress_cb:
+        progress_cb("Loading segmentation model…")
+
+    start_time = time.time()
+    seg = Segmenter(vad_engine='smn', detect_gender=False)
+
+    if progress_cb:
+        progress_cb("Running audio segmentation (this may take a while)…")
+
+    segments = seg(wav_path)
+    elapsed = time.time() - start_time
+
+    if progress_cb:
+        progress_cb(f"Segmentation complete in {elapsed:.1f}s — {len(segments)} raw segments")
+
+    return segments
+
+
+def merge_singing_segments(
+    segments: list,
+    max_gap: float = 10.0,
+    min_duration: float = 20.0,
+    padding: float = 2.0,
+) -> list:
+    """
+    Filter for 'music' segments and merge nearby ones.
+    
+    Returns list of dicts:
+        [{"index", "start", "end", "duration", "original_start", "original_end"}, ...]
+    """
+    music_segs = [(start, end) for label, start, end in segments if label == "music"]
+
+    if not music_segs:
+        return []
+
+    music_segs.sort(key=lambda x: x[0])
+
+    # Merge segments with gaps smaller than max_gap
+    merged = []
+    current_start, current_end = music_segs[0]
+
+    for start, end in music_segs[1:]:
+        if start - current_end <= max_gap:
+            current_end = max(current_end, end)
+        else:
+            merged.append((current_start, current_end))
+            current_start, current_end = start, end
+    merged.append((current_start, current_end))
+
+    # Apply padding and minimum duration filter
+    results = []
+    idx = 1
+    for start, end in merged:
+        duration = end - start
+        if duration >= min_duration:
+            padded_start = max(0, start - padding)
+            padded_end = end + padding
+            results.append({
+                "index": idx,
+                "start": padded_start,
+                "end": padded_end,
+                "duration": padded_end - padded_start,
+                "original_start": start,
+                "original_end": end,
+            })
+            idx += 1
+
+    return results
+
+
+def get_segment_stats(segments: list) -> dict:
+    """Get summary statistics from raw segmentation output."""
+    type_counts = {}
+    type_durations = {}
+    for label, start, end in segments:
+        type_counts[label] = type_counts.get(label, 0) + 1
+        type_durations[label] = type_durations.get(label, 0) + (end - start)
+    return {
+        "counts": type_counts,
+        "durations": type_durations,
+    }