feat: ASRX hybrid pipeline, identity history, worker fixes, checkpoint system

scripts/asrx_self/vad.py

@@ -126,6 +126,52 @@ def extract_speech_audio(audio_path, model, utils, output_dir=None):
     return speech_audios, speech_segments
 
 
+def scan_within_segment(wav, sample_rate, start_sec, end_sec, model, utils,
+                        min_speech_duration_ms=500, min_silence_duration_ms=300):
+    """
+    在一個時間範圍內執行 VAD 掃描，切出子片段。
+
+    用途: whisper 給出的粗略時間段內，利用句間停頓細切。
+
+    Args:
+        wav: 完整音頻波形 (numpy array)
+        sample_rate: 採樣率
+        start_sec: 掃描起始時間 (秒)
+        end_sec: 掃描結束時間 (秒)
+        model: VAD 模型
+        utils: VAD 工具函數
+        min_speech_duration_ms: 最小語音持續時間
+        min_silence_duration_ms: 最小靜音持續時間
+
+    Returns:
+        sub_segments: [(start_sec, end_sec), ...] 子片段列表 (原始時間軸)
+    """
+    get_speech_timestamps, _, _, _, _ = utils
+
+    # 提取該時間範圍內的音頻
+    start_sample = int(start_sec * sample_rate)
+    end_sample = int(end_sec * sample_rate)
+    segment_wav = wav[start_sample:end_sample]
+
+    # 在子音頻上執行 VAD
+    speech_ts = get_speech_timestamps(
+        segment_wav,
+        model,
+        sampling_rate=sample_rate,
+        min_speech_duration_ms=min_speech_duration_ms,
+        min_silence_duration_ms=min_silence_duration_ms,
+        return_seconds=True,
+    )
+
+    # 轉換回原始時間軸
+    sub_segments = [
+        (ts["start"] + start_sec, ts["end"] + start_sec)
+        for ts in speech_ts
+    ]
+
+    return sub_segments
+
+
 if __name__ == "__main__":
     # 測試 VAD
     import sys