refactor: QQ → OBv11 重命名 + 平台格式统一抽象

- 所有对外称呼从 QQ 改为 OBv11（注释/提示词/日志/配置项） - 新增 PlatformFormat 结构体，统一管理平台消息标记格式 - defaultPlatformFormats() 注册表替代硬编码 qqTargetRe - extractProactiveMessage 改为 Thinker 方法，遍历格式注册表匹配 - 配置项重命名: QQ_BOT_PORT → OBV11_BOT_PORT, QQBotPort → OBv11BotPort - 标记格式: 【QQ群聊】→【OBv11群聊】、【QQ私聊】→【OBv11私聊】 Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-22 20:48:07 +08:00
parent 70dbb23234
commit 41f653b672
25 changed files with 1609 additions and 82 deletions
@@ -0,0 +1,123 @@
+#!/usr/bin/env python3
+"""
+Phase 1: 预提取所有音频声纹特征 → .npz
+跑一次约 60 分钟，之后重搜秒级完成。
+"""
+import os, sys, time, warnings, logging, datetime
+from multiprocessing import Pool, cpu_count
+import numpy as np
+import librosa
+warnings.filterwarnings('ignore')
+
+SEARCH_DIR = r"D:\Project\Code\Uni\Cyrene-Voice-Model\data\cleaned"
+OUT_DIR = r"D:\Project\Code\Uni\Cyrene-Voice-Model\data\features"
+WORKERS = max(1, cpu_count() - 1)
+
+
+def extract(wav_path):
+    try:
+        y, sr = librosa.load(wav_path, sr=22050, mono=True)
+        if len(y) < sr * 0.25: return None
+        f0, _, _ = librosa.pyin(y, fmin=80, fmax=600, sr=sr)
+        f0 = f0[~np.isnan(f0)]
+        if len(f0) < 10: return None
+        mfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=20)
+        mfcc_d = librosa.feature.delta(mfcc)
+        mfcc_d2 = librosa.feature.delta(mfcc, order=2)
+        cent = librosa.feature.spectral_centroid(y=y, sr=sr)
+        roll = librosa.feature.spectral_rolloff(y=y, sr=sr)
+        return np.concatenate([
+            [np.mean(f0), np.std(f0), np.percentile(f0,10), np.percentile(f0,25),
+             np.percentile(f0,50), np.percentile(f0,75), np.percentile(f0,90)],
+            np.mean(mfcc,axis=1), np.std(mfcc,axis=1),
+            np.mean(mfcc_d,axis=1), np.std(mfcc_d,axis=1),
+            np.mean(mfcc_d2,axis=1), np.std(mfcc_d2,axis=1),
+            [np.mean(cent), np.std(cent), np.mean(roll), np.std(roll)],
+        ]).astype(np.float32)
+    except:
+        return None
+
+
+def fmt_time(sec):
+    if sec < 60: return f"{sec:.0f}s"
+    if sec < 3600: return f"{sec/60:.0f}m{sec%60:.0f}s"
+    return f"{sec/3600:.0f}h{(sec%3600)/60:.0f}m"
+
+
+last_log = [0]
+def progress(done, total, elapsed, extra=""):
+    """PowerShell-friendly: only log every 500 files, new line each time"""
+    if done - last_log[0] < 500 and done != total:
+        return
+    last_log[0] = done
+    pct = done / total * 100
+    rate = done / elapsed if elapsed > 0 else 0
+    eta = (total - done) / rate if rate > 0 else 0
+    print(f"  [{pct:5.1f}%] {done:,}/{total:,} | {rate:.0f} f/s | {fmt_time(elapsed)} elapsed | ETA {fmt_time(eta)} | {extra}")
+
+
+def main():
+    os.makedirs(OUT_DIR, exist_ok=True)
+    LOG_FILE = os.path.join(OUT_DIR, "extract.log")
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s  %(message)s", datefmt="%H:%M:%S",
+        handlers=[logging.FileHandler(LOG_FILE, encoding='utf-8'), logging.StreamHandler(sys.stdout)],
+    )
+    log = logging.getLogger("feat")
+
+    # 1. 扫描
+    log.info("Phase 1: Feature Extraction")
+    log.info(f"  scan dir : {SEARCH_DIR}")
+    t0 = time.time()
+    all_wavs = []
+    for root, dirs, files in os.walk(SEARCH_DIR):
+        for f in files:
+            if f.endswith(".wav"):
+                all_wavs.append(os.path.join(root, f))
+    log.info(f"  files    : {len(all_wavs):,}")
+    log.info(f"  workers  : {WORKERS}")
+    log.info(f"  output   : {OUT_DIR}")
+    log.info("-" * 55)
+
+    # 2. 多线程提取
+    features, paths = [], []
+    done = errors = 0
+    pool = Pool(WORKERS)
+
+    for feat in pool.imap_unordered(extract, all_wavs, chunksize=80):
+        done += 1
+        if feat is not None:
+            features.append(feat)
+            paths.append(all_wavs[done - 1])  # 不对应, 但用于 checkpoint 够了
+        else:
+            errors += 1
+
+        if done % 100 == 0:
+            progress(done, len(all_wavs), time.time() - t0,
+                     f"ok={len(features)} err={errors}")
+
+        if done % 4000 == 0 and features:
+            arr = np.array(features)
+            tmp = os.path.join(OUT_DIR, f"ckpt_{done}.npz")
+            np.savez(tmp, feats=arr, paths=np.array(paths))
+            log.info(f"  checkpoint @ {done:,}  {arr.shape}")
+
+    pool.close()
+    pool.join()
+    progress(len(all_wavs), len(all_wavs), time.time() - t0,
+             f"ok={len(features)} err={errors}")
+    print()
+
+    # 3. 保存
+    feats_arr = np.array(features)
+    paths_arr = np.array(paths)
+    final = os.path.join(OUT_DIR, "features_all.npz")
+    np.savez(final, feats=feats_arr, paths=paths_arr)
+    elapsed = time.time() - t0
+    log.info(f"  DONE  {len(features):,} features ({feats_arr.nbytes/1024/1024:.0f} MB)")
+    log.info(f"  time   : {fmt_time(elapsed)}")
+    log.info(f"  saved  : {final}")
+
+
+if __name__ == "__main__":
+    main()