From 723337b45280acdcf4acd74c7fcdebf01399bfbe Mon Sep 17 00:00:00 2001 From: Fisto Date: Tue, 22 Sep 2026 19:52:29 +0200 Subject: [PATCH] Merge the SAM VOX preset tuning and comparison tool --- CURRENT.md | 9 ++ microslopsam/README.md | 21 +++-- microslopsam/docs/NOTES.md | 16 ++-- microslopsam/docs/TTS-DESIGN.md | 79 +++++++++++++---- microslopsam/setup/test-wrapper.sh | 8 +- microslopsam/setup/veskslop-tts.sh | 16 ++-- microslopsam/tools/vox_compare.py | 134 +++++++++++++++++++++++++++++ 7 files changed, 245 insertions(+), 38 deletions(-) create mode 100755 microslopsam/tools/vox_compare.py diff --git a/CURRENT.md b/CURRENT.md index b519fc6..c701565 100644 --- a/CURRENT.md +++ b/CURRENT.md @@ -40,6 +40,15 @@ mobile draft at 390px. - [x] C11 preview caching: Discord-hosted image/GIF previews (WebP 320px, hash-addressed, 5 MiB cap, one attempt) run after every walk in both modes. Live run `...-20260916090722`: `previewed: 2`; thumbs served over `/api/media///thumb` (200). + - [x] C83 Merge the SAM updates. `~/Projects/Sam/MicroslopSam` moved ahead (VOX preset tuned + against the game word assets, `tools/vox_compare.py`, docs, wrapper/test sync). The updates + matched our tree except the local `microslopsam.env` paths, so the merge is: the retuned VOX + profile (pitch 0, rate 15, head 34, lowering 50), the matching test expectations, the README + and design-doc updates, and the new comparison tool. **Also regenerated `poc/.env`'s + `VESKSLOP_TTS_VOICES`** (gitignored) from `setup/veskslop-tts.sh --voices` so the UI profile + defaults match what the wrapper writes — without it the panel would have offered the old snap + points. Wrapper tests pass; a live vox preview renders. A stored profile override keeps the old + tuning until it is double-clicked back to the profile default. - [x] C82 Double-click resets in the voice settings. Every slider in the TTS panel resets on double-click: the voice-character profile sliders (to the voice's **profile default**), expression (the profile default, and the override is truly cleared so the label reads diff --git a/microslopsam/README.md b/microslopsam/README.md index aced4de..3389bc1 100644 --- a/microslopsam/README.md +++ b/microslopsam/README.md @@ -73,8 +73,8 @@ Options: `-v` voice, `-t` text, `-o` output WAV, `-p` pitch, `-s` speed, `-V` vo export VESKSLOP_TTS_CMD="$PWD/setup/veskslop-tts.sh {out} {text_file}" export VESKSLOP_TTS_VOICES="$(setup/veskslop-tts.sh --voices)" -The wrapper maps voice IDs (`sam`, `mary`, `mike`, `keith-bell`, `kerry-watson`, plus the -MSTTS variants), reads `VESKSLOP_TTS_VOICE`, `VESKSLOP_TTS_SPEED` (multiplier), +The wrapper maps voice IDs (`sam`, `mary`, `mike`, `keith-bell`, `kerry-watson`, `vox`, +`hev`, plus the MSTTS variants), reads `VESKSLOP_TTS_VOICE`, `VESKSLOP_TTS_SPEED` (multiplier), `VESKSLOP_TTS_PITCH` (semitones) and `VESKSLOP_TTS_EXPRESSION` (0-100, Flextalk voices only), starts Xvfb when `DISPLAY` is unset, and writes a 48 kHz mono s16le WAV trimmed, faded and normalized to about -16 LUFS (-3 dBFS true peak). @@ -93,9 +93,18 @@ A short low-level leading hum (80 ms, 75 Hz, -48 dBFS) primes Discord's audio pi so the first word is not gated; tune with `VESKSLOP_TTS_HUM_MS` (0 = off), `VESKSLOP_TTS_HUM_HZ`, and `VESKSLOP_TTS_HUM_DB`. -**Half-Life presets** (Keith Bell): `VESKSLOP_TTS_PRESET=vox` applies the approximated -Valve VOX profile and enables VOX prosody; `VESKSLOP_TTS_PRESET=hev` is a starting point -for the HEV suit voice. Values are in `docs/TTS-DESIGN.md`. +**Half-Life presets** (Keith Bell): `VESKSLOP_TTS_PRESET=vox` applies the Valve VOX +profile (pitch 0, rate 15, head size 34, lowering 50) and enables VOX prosody; +`VESKSLOP_TTS_PRESET=hev` is a starting point for the HEV suit voice. The `vox` and `hev` +voice IDs select these directly. The VOX values were +tuned against the game's word assets with `tools/vox_compare.py`; details in +`docs/TTS-DESIGN.md`. + +`VESKSLOP_TTS_CRUNCH` (`hl90`, `hl90hq`, `telephone`, `adpcm`, `crush`) adds 1990s lossy +character to the output; `VESKSLOP_TTS_CRUNCH_BITS`/`_RATE` override its bit depth and +sample rate. `VESKSLOP_TTS_STREAM=1` makes word mode write the WAV as it goes (no +measurement pass; `VESKSLOP_TTS_STREAM_GAIN_DB` sets the gain). Echo timing and level are +`VESKSLOP_TTS_ECHO_DELAY_MS` and `VESKSLOP_TTS_ECHO_LEVEL`. ## Layout @@ -107,7 +116,9 @@ for the HEV suit voice. Values are in `docs/TTS-DESIGN.md`. - `setup/inf2reg.py` — INF AddReg -> `.reg` converter - `setup/run.sh` — run helper (prefix + Xvfb) - `setup/veskslop-tts.sh` — Veskslop command-provider wrapper (post-processing included) +- `setup/test-wrapper.sh` — wrapper regression test (stubbed Wine/host, no prefix needed) - `setup/vox_parser.py` — NetTTS-style VOX prosody encoder (Flextalk voices) +- `tools/vox_compare.py` — reference-vs-synthesis metrics for preset tuning - `docs/NOTES.md` — registry/CLSID facts, runtime RE notes, gotchas - `docs/TTS-DESIGN.md` — integration contract with Veskslop plus engine clarifications diff --git a/microslopsam/docs/NOTES.md b/microslopsam/docs/NOTES.md index 8541c1d..a7be815 100644 --- a/microslopsam/docs/NOTES.md +++ b/microslopsam/docs/NOTES.md @@ -127,12 +127,16 @@ without them. the Python port; outputs are identical on the 31-line corpus. Re-check after any parser change while the clone is available. - VOX mode is Flextalk-only. The wrapper enables it with `VESKSLOP_TTS_VOX=1` - (`VESKSLOP_TTS_VOX_CLEAN=1` drops the stutter wrapper) and it takes precedence - over `VESKSLOP_TTS_WORDS`. -- Half-Life presets (`VESKSLOP_TTS_PRESET=vox|hev`) target Keith Bell only. VOX values - come from NetTTS `nettts_flextalk_vox_profile.reg`: pitch 3, rate 17, prominences 22, - head size 52, volume 70 (factory: 27/33/17/46/100); `vox` also implies VOX prosody. - `hev` (pitch 15, rate 24) is an unverified starting point - HL1 credits the suit + (`VESKSLOP_TTS_VOX_CLEAN=1` drops the stutter wrapper); word mode + (`VESKSLOP_TTS_WORDS=1`) wins and skips VOX prosody. +- Half-Life presets (`VESKSLOP_TTS_PRESET=vox|hev`) target Keith Bell only. VOX starts + from NetTTS `nettts_flextalk_vox_profile.reg` (pitch 3, rate 17, head 52, lowering 40) + and is tuned against the game's word assets from `suchipi/half-life-vox-console`: + shipped values are pitch 0, rate 15, prominences 22, head size 34, lowering 50, + volume 70. Measured on 38 words vs the game assets: F0 82.3 vs 82.3 Hz, duration + 22.99 vs 23.36 s, >2 kHz share 0.0172 vs 0.0186 (old approximation: 87.5 Hz / + 22.28 s / 0.0137). `tools/vox_compare.py` reproduces the comparison. `hev` + (pitch 15, rate 24) remains an unverified starting point - HL1 credits the suit sounds to Kelly Bailey with no published settings. - Flextalk rate/pitch are applied as **vendor tags** (`\!R` = duration factor, `\!%` = pitch multiplier), never `-s`/`-p`, because ITTSAttributes override the diff --git a/microslopsam/docs/TTS-DESIGN.md b/microslopsam/docs/TTS-DESIGN.md index 027af6f..292ad62 100644 --- a/microslopsam/docs/TTS-DESIGN.md +++ b/microslopsam/docs/TTS-DESIGN.md @@ -254,6 +254,9 @@ record what the engine needs to interpret, add, or hide._ - Assigned stable IDs: `sam`, `mary`, `mike`, `keith-bell`, `kerry-watson`; variants get `mike-telephone`, `mike-hall`, `mary-stadium`, `mike-space`, and so on. Unknown IDs fall back to `sam`. +- `vox` (VOX (Half-Life)) and `hev` (HEV suit) are Keith Bell with a fixed preset profile; + selecting one implies `VESKSLOP_TTS_PRESET` (`vox` also enables VOX prosody). Their + `defaults=` metadata follows the active preset so the UI snap points match. - `/voices` (HTTP mode) reports `language: "en"`, gender, and the speed/pitch ranges below. ### Speed and pitch mapping (measured 2026-09-15) @@ -372,15 +375,16 @@ Requirements and scope: The host passes `TTSDATAFLAG_TAGGED`, so the engine honors them. Other voices ignore `VESKSLOP_TTS_VOX`. - Needs `python3` at runtime; the wrapper fails loudly when it is missing. -- Mutually exclusive with `VESKSLOP_TTS_WORDS` (VOX wins). +- Combines with `VESKSLOP_TTS_WORDS`: word mode wins and VOX prosody is skipped. - Measured on the dev host for "Now approaching Sector C test lab. Please stand clear of the test chamber.": plain 4.70 s with 1 pause, VOX 7.81 s with 8 pauses. Other NetTTS features and their relevance: -- Inline `/rate N`, `/pitch N`, `[[pause N]]`: not ported. Veskslop has speed/pitch - controls and the profile window; `[[pause N]]` could be added as a wrapper-level - text splitter later (NetTTS supports it only outside VOX mode). +- Inline `/rate N`, `/pitch N` are handled by the wrapper at the start of a line + (percent, or a multiplier at or below 2.0); they override the env sliders for that + line and are not spoken. `[[pause N]]` is not ported; it could be added as a + wrapper-level text splitter later. - TCP server with `START`/`STOP` status sockets: not needed; Veskslop owns playback and knows when a line ends. - Winetricks prefix automation (`winxp`, `vcrun6`, `mfc42`, `riched20`): not needed; @@ -398,16 +402,20 @@ Kerry Watson at factory values. The wrapper implements it as a preset: VESKSLOP_TTS_PRESET=vox # implies VOX prosody unless VESKSLOP_TTS_VOX is set VESKSLOP_TTS_PRESET=hev # HEV suit starting point (see note below) -| Profile value | Factory (Keith) | VOX preset | HEV preset (approx.) | +| Profile value | Factory (Keith) | VOX preset (tuned) | HEV preset (approx.) | | --- | --- | --- | --- | -| Pitch | 27 | 3 | 15 | -| Speaking Rate | 33 | 17 | 24 | +| Pitch | 27 | 0 | 15 | +| Speaking Rate | 33 | 15 | 24 | | Prominences | 17 | 22 | 22 | -| Head Size | 46 | 52 | 52 | -| Lowering | 40 | 40 | 40 | +| Head Size | 46 | 34 | 52 | +| Lowering | 40 | 50 | 40 | | Volume | 100 | 70 | 70 | | Expression | 59 | 59 | 59 | +The VOX column starts from NetTTS's approximation (pitch 3, rate 17, head 52, lowering +40) and is refined against the actual game word assets; see +"Tuning against the actual game assets" below. + - Presets apply only to `keith-bell`; every other voice keeps its defaults. - Precedence: preset < `VESKSLOP_TTS_PROFILE` < `VESKSLOP_TTS_EXPRESSION`. - Equivalent explicit override: @@ -465,16 +473,49 @@ Verified matrix (same line, Keith Bell): | Run | Duration | F0 median | | --- | --- | --- | | factory, no adjustments | 3.35 s | 123 Hz | -| VOX preset, no adjustments | 5.83 s | 87 Hz | -| VOX preset + `speed=1.0 pitch=0` | 5.83 s, byte-identical | 87 Hz | -| VOX preset + `speed=1.3` | 4.02 s | 84 Hz | -| VOX preset + `pitch=+3` | 5.83 s | 88 Hz | -| HEV preset, no adjustments | 3.79 s | - | +| VOX preset, no adjustments | 6.06 s | 82 Hz | +| VOX preset + `speed=1.0 pitch=0` | 6.06 s, byte-identical | 82 Hz | +| VOX preset + `speed=1.3` | 4.02 s | - | +| VOX preset + `pitch=+3` | 6.06 s | 96 Hz | Registry inspection after a preset run: 26 values in the Keith speaker key in both -hives, `Pitch=0x3`, `Speaking Rate=0x11`, `Gender=0x2`, `Line Mode=0x1`, +hives, `Pitch=0x0`, `Speaking Rate=0xf`, `Head Size=0x22`, `Lowering=0x32`, +`Gender=0x2`, `Line Mode=0x1`, `Default Speaker={11260610-C84A-11CE-AEC4-0000C0E9CB87}`. +#### Tuning against the actual game assets (2026-09-22) + +Reference: the word WAVs from `suchipi/half-life-vox-console` +(`public/vox/*.wav`, Valve assets - used locally for analysis only, never committed). +38 words at 11025 Hz 16-bit, the engine's native rate. `tools/vox_compare.py` +reproduces the comparison; it reports the cepstrum F0 median, total audible duration, +energy-weighted spectral centroid and the >2 kHz energy share per word set. + +| Metric (38 words) | Game assets | NetTTS approximation | Shipped VOX preset | +| --- | --- | --- | --- | +| F0 median | 82.3 Hz | 87.5 Hz | 82.3 Hz | +| Duration | 23.36 s | 22.28 s | 22.99 s | +| Spectral centroid | 515 Hz | 479 Hz | 453 Hz | +| >2 kHz energy share | 0.0186 | 0.0137 | 0.0172 | + +Findings: + +- Registry `Pitch 0` is the engine minimum and matches the game's F0; the NetTTS + approximation (3) was about 5 Hz high. +- `Speaking Rate 15` matches the word durations within about 1.6%; NetTTS's 17 was + about 4.6% fast on this corpus. +- The game voice is brighter than the approximation. Smaller `Head Size` raises + brightness (34 is the engine's effective minimum here; 30 gives identical output) and + `Lowering 50` adds a little more, together closing most of the >2 kHz gap + (0.0137 -> 0.0172 against 0.0186). +- The residual centroid difference is mostly the reference's mid/high-band noise floor + (game assets), not voice timbre. +- HEV stays a starting point: no published settings and no word-level reference exists. + +Re-run recipe: write the profile to both hives, synthesize the reference word list with +`build/sapi4host-winlib.exe -v "Keith Bell" -t -o /.wav`, then +`tools/vox_compare.py `. + ### Inline rate/pitch controls (engine-side) The wrapper consumes NetTTS-style, line-leading controls, so Veskslop and the WebUI do @@ -666,9 +707,15 @@ Inputs: `{out}`, `{text_file}`, optional positional voice/speed/pitch/expression | `VESKSLOP_TTS_PROFILE` | `pitch:27:...`/`key=value,...` overrides; the wrapper writes the full profile (defaults + overrides) to the Wine registry with `wine reg import` before every synthesis. | | `VESKSLOP_TTS_HIGHPASS` | High-pass Hz, 40-400 (default 40). | | `VESKSLOP_TTS_ECHO` | Mono echo 0-100 (`aecho`), default 0. The echo is mixed under the dry voice, so the voice level does not change. | +| `VESKSLOP_TTS_ECHO_DELAY_MS` / `VESKSLOP_TTS_ECHO_LEVEL` | Echo delay 10-400 ms (default 60) and repeat level 0-0.95 relative to the dry voice (default 0.85). | +| `VESKSLOP_TTS_CRUNCH` | `off` (default) or `hl90`, `hl90hq`, `telephone`, `adpcm`, `crush`: 1990s lossy character, applied last. | +| `VESKSLOP_TTS_CRUNCH_BITS` / `VESKSLOP_TTS_CRUNCH_RATE` | Bit depth 1-16 and sample rate 4000-48000 overrides for the crunch stage. | +| `VESKSLOP_TTS_STREAM` / `VESKSLOP_TTS_STREAM_GAIN_DB` | `1` = word mode writes the WAV as it goes (no measurement pass); fixed gain in dB for that path. | | `VESKSLOP_TTS_WORDS` / `VESKSLOP_TTS_WORD_GAP_MS` | Word-by-word synthesis with silence gaps (Flextalk only). | -Placeholders `{profile}`, `{highpass}`, `{echo}`, `{words}`, `{word_gap_ms}` mirror the env vars. +Placeholders `{profile}`, `{highpass}`, `{echo}`, `{echo_delay_ms}`, `{echo_level}`, +`{words}`, `{word_gap_ms}`, `{crunch}`, `{crunch_bits}`, `{crunch_rate}`, `{stream}`, +`{vox}`, `{vox_clean}`, `{preset}` mirror the env vars. `wine regedit` fails headlessly but returns 0: use `wine reg import`. A missing profile value must always write the engine default so no stale registry state survives. diff --git a/microslopsam/setup/test-wrapper.sh b/microslopsam/setup/test-wrapper.sh index a218309..0144efd 100755 --- a/microslopsam/setup/test-wrapper.sh +++ b/microslopsam/setup/test-wrapper.sh @@ -94,8 +94,8 @@ check "vox preset implies VOX parser" "1" "$(grep -c 'wH1' "$STUB_LOG")" # The preset writes the full audible profile to both hives. VESKSLOP_TTS_VOICE=keith-bell VESKSLOP_TTS_PRESET=vox run_wrapper check "preset writes both hives" "2" "$(grep -c 'Speakers\\{11260610' "$STUB_REG")" -check "preset pitch (both hives)" "2" "$(grep -c '"Pitch"=dword:00000003' "$STUB_REG")" -check "preset rate (both hives)" "2" "$(grep -c '"Speaking Rate"=dword:00000011' "$STUB_REG")" +check "preset pitch (both hives)" "2" "$(grep -c '"Pitch"=dword:00000000' "$STUB_REG")" +check "preset rate (both hives)" "2" "$(grep -c '"Speaking Rate"=dword:0000000f' "$STUB_REG")" check "preset gender and line mode" "4" "$(grep -cE '"Gender"=dword:00000002|"Line Mode"=dword:00000001' "$STUB_REG")" check "preset default speaker" "2" "$(grep -c '"Default Speaker"' "$STUB_REG")" @@ -111,7 +111,7 @@ check "word mode with preset synthesizes every word" "3" "$(grep -c '^ARGV:' "$S check "word mode skips the VOX parser" "0" "$(grep -c 'wH1' "$STUB_LOG")" check "word mode tags every word" "3" \ "$(sed -n 's/.*\[-t\] \[\(.*\)\] \[-o\].*/\1/p' "$STUB_LOG" | grep -c '^\\!R0.80 ')" -check "word mode keeps the preset profile" "2" "$(grep -c '"Pitch"=dword:00000003' "$STUB_REG")" +check "word mode keeps the preset profile" "2" "$(grep -c '"Pitch"=dword:00000000' "$STUB_REG")" check "word mode emits no attributes" "0" "$(attr_count)" # The vox preset implies VOX when the variable is unset, but word mode still wins. @@ -139,7 +139,7 @@ check "stream has a gap per word break" "2" \ # The Half-Life voices carry their profile preset. VESKSLOP_TTS_VOICE=vox VESKSLOP_TTS_VOX=1 run_wrapper -check "vox voice writes the VOX profile (both hives)" "2" "$(grep -c '"Pitch"=dword:00000003' "$STUB_REG")" +check "vox voice writes the VOX profile (both hives)" "2" "$(grep -c '"Pitch"=dword:00000000' "$STUB_REG")" check "vox voice runs VOX prosody" "1" "$(grep -c 'wH1' "$STUB_LOG")" VESKSLOP_TTS_VOICE=hev run_wrapper check "hev voice writes the HEV profile (both hives)" "2" "$(grep -c '"Pitch"=dword:0000000f' "$STUB_REG")" diff --git a/microslopsam/setup/veskslop-tts.sh b/microslopsam/setup/veskslop-tts.sh index 359b885..ee6737a 100755 --- a/microslopsam/setup/veskslop-tts.sh +++ b/microslopsam/setup/veskslop-tts.sh @@ -46,7 +46,7 @@ ROOT=$MICROSLOP_ROOT # The Keith Bell defaults follow the active preset so the UI's "default" snap points # match the values the preset actually writes. -VOX_DEFAULTS="pitch:3:rate:17:prominences:22:head_size:52:lowering:40:expression:59" +VOX_DEFAULTS="pitch:0:rate:15:prominences:22:head_size:34:lowering:50:expression:59" HEV_DEFAULTS="pitch:15:rate:24:prominences:22:head_size:52:lowering:40:expression:59" case "${VESKSLOP_TTS_PRESET:-}" in vox) KB_DEFAULTS="$VOX_DEFAULTS" ;; @@ -243,15 +243,17 @@ if [ -n "$SPEAKER_GUID" ]; then P_LOWER=40 P_EXPR="" - # Half-Life presets for Keith Bell (the game's announcement voice). - # "vox" is the approximated Valve VOX profile published by NetTTS - # (scripts/winetricks/nettts_flextalk_vox_profile.reg); "hev" is a starting - # point for the HEV suit voice, which has no published profile. + # Half-Life presets for Keith Bell (the game's announcement voice). "vox" + # starts from the approximated Valve VOX profile published by NetTTS + # (scripts/winetricks/nettts_flextalk_vox_profile.reg), then refines pitch, + # rate, head size and lowering against the actual game word assets + # (see docs/TTS-DESIGN.md). "hev" is a starting point for the HEV suit + # voice, which has no published profile. case "$PRESET" in vox) if [ "$ENGVOICE" = "Keith Bell" ]; then - P_PITCH=3; P_RATE=17; P_VOLUME=70 - P_PROM=22; P_HEAD=52; P_LOWER=40 + P_PITCH=0; P_RATE=15; P_VOLUME=70 + P_PROM=22; P_HEAD=34; P_LOWER=50 fi ;; hev) diff --git a/microslopsam/tools/vox_compare.py b/microslopsam/tools/vox_compare.py new file mode 100755 index 0000000..3853588 --- /dev/null +++ b/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=" 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())