cleanup: remove dead code and duplicate docs
- Remove session-ses_2f27.md (161KB raw session log) - Remove 49 ROOT_* duplicate files across REFERENCE/ - Remove 14 duplicate files between REFERENCE/ root and history/ - Remove asr_legacy.rs (dead code, replaced by asr.rs) - Remove src/core/worker/ (duplicate JobWorker) - Remove src/core/layers/ (empty directory) - Remove 4 .bak files in src/ - Remove 7 dead private methods in worker/processor.rs - Remove backup directory from git tracking
This commit is contained in:
Warren
@@ -134,7 +134,7 @@ class SelfASRXFixed:
|
||||
result["processing_time"] = round(total_time, 2)
|
||||
result["realtime_factor"] = round(result["total_duration"] / total_time, 2)
|
||||
|
||||
print(f"\n[SelfASRX-Fixed] Processing completed!")
|
||||
print("\n[SelfASRX-Fixed] Processing completed!")
|
||||
print(f" Total time: {total_time:.2f}s")
|
||||
print(f" Realtime factor: {result['realtime_factor']:.2f}x")
|
||||
print(f" Detected speakers: {estimated_n_speakers}")
|
||||
@@ -154,6 +154,117 @@ class SelfASRXFixed:
|
||||
return result
|
||||
|
||||
|
||||
def process_with_segments(self, audio_path, asr_segments, output_path=None):
|
||||
"""
|
||||
使用 ASR segment 邊界進行 speaker diarization，取代 VAD 步驟。
|
||||
|
||||
Args:
|
||||
audio_path: 音頻文件路徑（WAV）
|
||||
asr_segments: ASR segment 列表，每個包含 start/end（秒）
|
||||
output_path: 輸出 JSON 路徑（可選）
|
||||
"""
|
||||
start_time = time.time()
|
||||
print(f"\n[SelfASRX-Fixed] Processing with {len(asr_segments)} ASR segments: {audio_path}")
|
||||
print("=" * 60)
|
||||
|
||||
# 載入完整音頻
|
||||
import soundfile as sf
|
||||
wav, sample_rate = sf.read(audio_path)
|
||||
if len(wav.shape) > 1:
|
||||
wav = np.mean(wav, axis=1) # 轉 mono
|
||||
print(f" Audio loaded: {len(wav)/sample_rate:.2f}s, {sample_rate}Hz")
|
||||
|
||||
# 使用 ASR segments 取代 VAD
|
||||
speech_segments = [(s["start"], s["end"]) for s in asr_segments]
|
||||
print(f" Speech segments from ASR: {len(speech_segments)}")
|
||||
|
||||
if len(speech_segments) == 0:
|
||||
print("[SelfASRX-Fixed] No ASR segments provided!")
|
||||
return {"error": "No ASR segments", "segments": []}
|
||||
|
||||
# 提取語音片段
|
||||
audio_segments = []
|
||||
for start_sec, end_sec in speech_segments:
|
||||
start_sample = int(start_sec * sample_rate)
|
||||
end_sample = int(end_sec * sample_rate)
|
||||
if start_sample >= len(wav):
|
||||
continue
|
||||
audio_segments.append(wav[start_sample:min(end_sample, len(wav))])
|
||||
|
||||
print(f" Audio segments extracted: {len(audio_segments)}")
|
||||
|
||||
# 批量提取聲紋嵌入
|
||||
print("\n[Step 2] Speaker embedding extraction...")
|
||||
step2_start = time.time()
|
||||
embeddings = extract_speaker_embeddings_batch(
|
||||
self.speaker_encoder, audio_segments, sample_rate
|
||||
)
|
||||
embeddings = normalize_embeddings(embeddings)
|
||||
step2_time = time.time() - step2_start
|
||||
print(f" Embedding shape: {embeddings.shape}")
|
||||
print(f" Embedding time: {step2_time:.2f}s")
|
||||
|
||||
# 聚類
|
||||
print("\n[Step 3] Robust speaker clustering...")
|
||||
step3_start = time.time()
|
||||
speaker_labels, estimated_n_speakers = robust_speaker_clustering(
|
||||
embeddings, n_speakers=None, max_speakers=10
|
||||
)
|
||||
step3_time = time.time() - step3_start
|
||||
print(f" Clustering time: {step3_time:.2f}s")
|
||||
|
||||
# 建立輸出
|
||||
result = {
|
||||
"audio_path": str(audio_path),
|
||||
"total_duration": len(wav) / sample_rate,
|
||||
"n_speech_segments": len(speech_segments),
|
||||
"n_speakers": int(estimated_n_speakers),
|
||||
"segments": []
|
||||
}
|
||||
|
||||
for i, ((start, end), label) in enumerate(zip(speech_segments, speaker_labels)):
|
||||
result["segments"].append({
|
||||
"index": i,
|
||||
"start": round(start, 3),
|
||||
"end": round(end, 3),
|
||||
"duration": round(end - start, 3),
|
||||
"speaker": f"SPEAKER_{int(label)}"
|
||||
})
|
||||
|
||||
# 加入 embeddings（每個 segment 對應的 192-D speaker embedding）
|
||||
result["embeddings"] = []
|
||||
for emb in embeddings:
|
||||
result["embeddings"].append(emb.tolist())
|
||||
|
||||
# 統計
|
||||
speaker_stats = {}
|
||||
for seg in result["segments"]:
|
||||
speaker = seg["speaker"]
|
||||
if speaker not in speaker_stats:
|
||||
speaker_stats[speaker] = {"count": 0, "duration": 0}
|
||||
speaker_stats[speaker]["count"] += 1
|
||||
speaker_stats[speaker]["duration"] += seg["duration"]
|
||||
result["speaker_stats"] = speaker_stats
|
||||
|
||||
total_time = time.time() - start_time
|
||||
result["processing_time"] = round(total_time, 2)
|
||||
result["realtime_factor"] = round(result["total_duration"] / total_time, 2)
|
||||
|
||||
print("\n[SelfASRX-Fixed] Processing completed!")
|
||||
print(f" Total time: {total_time:.2f}s")
|
||||
print(f" Realtime factor: {result['realtime_factor']:.2f}x")
|
||||
print(f" Detected speakers: {estimated_n_speakers}")
|
||||
|
||||
if output_path:
|
||||
import json
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
json.dump(result, f, indent=2, ensure_ascii=False)
|
||||
print(f" Results saved to: {output_path}")
|
||||
|
||||
print("=" * 60)
|
||||
return result
|
||||
|
||||
|
||||
def main():
|
||||
import argparse
|
||||
|
||||
@@ -180,14 +291,14 @@ def main():
|
||||
)
|
||||
|
||||
if "error" not in result:
|
||||
print(f"\n[Summary]")
|
||||
print("\n[Summary]")
|
||||
print(f" Audio duration: {result['total_duration']:.2f}s")
|
||||
print(f" Speech segments: {result['n_speech_segments']}")
|
||||
print(f" Detected speakers: {result['n_speakers']}")
|
||||
print(f" Processing time: {result['processing_time']:.2f}s")
|
||||
print(f" Realtime factor: {result['realtime_factor']:.2f}x")
|
||||
|
||||
print(f"\n[Speaker Statistics]")
|
||||
print("\n[Speaker Statistics]")
|
||||
for speaker, stats in result['speaker_stats'].items():
|
||||
pct = stats['duration'] / result['total_duration'] * 100
|
||||
print(f" {speaker}: {stats['count']} segments, " +
|
||||
|
||||
Reference in New Issue
Block a user