Merge the SAM VOX preset tuning and comparison tool

microslopsam/tools/vox_compare.py

@@ -0,0 +1,134 @@
+#!/usr/bin/env python3
+"""Compare synthesized words against reference WAV directories.
+
+Used to tune the Half-Life VOX preset against the game's word assets
+(`suchipi/half-life-vox-console`, `public/vox/*.wav` - Valve assets, keep them
+outside this repository).
+
+Usage:
+    vox_compare.py REFERENCE_DIR SYNTH_DIR [SYNTH_DIR ...]
+
+Directories must hold the same word file names (one WAV per word). Prints, per
+directory: median F0 (cepstrum), total audible duration, energy-weighted
+spectral centroid and the >2 kHz energy ratio. These are the metrics used to
+pick the VOX preset values in setup/veskslop-tts.sh.
+
+Requires numpy.
+"""
+import os
+import sys
+
+import numpy as np
+import wave
+
+
+def frames(path):
+    with wave.open(path) as w:
+        data = w.readframes(w.getnframes())
+        rate = w.getframerate()
+    samples = np.frombuffer(data, dtype="<i2").astype(float)
+    loud = np.nonzero(np.abs(samples) > 200)[0]
+    if len(loud) == 0:
+        return None, rate
+    return samples[loud[0]:loud[-1] + 1], rate
+
+
+def f0_cepstrum(seg, rate):
+    win = min(2048, (len(seg) // 2) * 2)
+    if win < 256:
+        return 0.0
+    values = []
+    for i in range(0, max(1, len(seg) - win), win // 2):
+        fr = seg[i:i + win]
+        if (fr ** 2).sum() < 1e6:
+            continue
+        fr = fr - fr.mean()
+        spectrum = np.abs(np.fft.rfft(fr * np.hanning(win))) + 1e-9
+        cepstrum = np.fft.irfft(np.log(spectrum))
+        lo, hi = int(rate / 400), int(rate / 60)
+        if hi <= lo:
+            continue
+        lag = lo + int(np.argmax(cepstrum[lo:hi]))
+        values.append(rate / lag)
+    values = sorted(v for v in values if 50 < v < 400)
+    return values[len(values) // 2] if values else 0.0
+
+
+def brightness(seg, rate):
+    win = min(2048, (len(seg) // 2) * 2)
+    cent, high, energy = [], [], []
+    for i in range(0, max(1, len(seg) - win), win // 2):
+        fr = seg[i:i + win]
+        if len(fr) < win:
+            break
+        e = (fr ** 2).sum() / win
+        if e < 1e5:
+            continue
+        fr = fr - fr.mean()
+        power = np.abs(np.fft.rfft(fr * np.hanning(win))) ** 2
+        freq = np.fft.rfftfreq(win, 1 / rate)
+        total = power.sum() + 1e-9
+        cent.append((power * freq).sum() / total)
+        high.append(power[(freq >= 2000) & (freq < 5000)].sum() / total)
+        energy.append(e)
+    if not cent:
+        return 0.0, 0.0
+    cent = np.array(cent)
+    high = np.array(high)
+    energy = np.array(energy)
+    keep = energy >= np.percentile(energy, 70)
+    return float(np.median(cent[keep])), float(np.median(high[keep]))
+
+
+def summarize(directory, words):
+    f0s, duration, cents, highs = [], 0.0, [], []
+    for word in words:
+        path = os.path.join(directory, word + ".wav")
+        if not os.path.exists(path):
+            continue
+        seg, rate = frames(path)
+        if seg is None or len(seg) == 0:
+            continue
+        duration += len(seg) / rate
+        value = f0_cepstrum(seg, rate)
+        if value > 0:
+            f0s.append(value)
+        c, h = brightness(seg, rate)
+        cents.append(c)
+        highs.append(h)
+    f0s.sort()
+    return {
+        "n": len(f0s),
+        "f0": f0s[len(f0s) // 2] if f0s else 0.0,
+        "dur": duration,
+        "cent": float(np.median(cents)) if cents else 0.0,
+        "high": float(np.median(highs)) if highs else 0.0,
+    }
+
+
+def main():
+    if len(sys.argv) < 3:
+        print(__doc__)
+        return 2
+    reference = sys.argv[1]
+    candidates = sorted(
+        name[:-4] for name in os.listdir(reference)
+        if name.endswith(".wav") and os.path.isfile(os.path.join(reference, name))
+    )
+    # Keep only words present in every directory so the summaries compare.
+    words = [
+        word for word in candidates
+        if all(os.path.exists(os.path.join(d, word + ".wav")) for d in sys.argv[1:])
+    ]
+    for directory in sys.argv[1:]:
+        s = summarize(directory, words)
+        print(
+            "%-28s words=%3d f0=%6.1fHz dur=%6.2fs cent=%5.0fHz high2k=%.4f"
+            % (os.path.basename(directory.rstrip("/")), s["n"], s["f0"], s["dur"],
+               s["cent"], s["high"])
+        )
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())