add memory_profiler

profile_diarization.py

@@ -1,62 +0,0 @@
-#!/usr/bin/env python3
-"""
-Memory profiling script for diarization
-"""
-
-import sys
-import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'src'))
-
-import numpy as np
-import soundfile as sf
-from memory_profiler import profile
-from diarization import init_speaker_embedding_extractor, perform_speaker_diarization_on_utterances
-from asr import transcribe_file
-
-def main():
-    # Load audio
-    audio_path = "example.mp3"
-    print(f"Loading audio from {audio_path}")
-    audio, sample_rate = sf.read(audio_path)
-    print(f"Audio loaded: {len(audio)} samples at {sample_rate}Hz")
-
-    # Resample to 16kHz if needed
-    if sample_rate != 16000:
-        from scipy.signal import resample
-        audio = resample(audio, int(len(audio) * 16000 / sample_rate))
-        sample_rate = 16000
-
-    # Ensure mono
-    if len(audio.shape) > 1:
-        audio = audio.mean(axis=1)
-
-    print(f"Audio prepared: {len(audio)} samples at {sample_rate}Hz")
-
-    # Perform ASR to get utterances
-    print("Starting ASR...")
-    utterances = []
-    for current, all_utterances in transcribe_file(
-        audio_path=audio_path,
-        vad_threshold=0.5,
-        model_name="moonshine/tiny",
-        backend="moonshine"
-    ):
-        utterances = all_utterances
-    print(f"ASR completed: {len(utterances)} utterances")
-
-    # Initialize embedding extractor
-    print("Initializing embedding extractor...")
-    embedding_extractor, config_dict = init_speaker_embedding_extractor()
-    if embedding_extractor is None:
-        print("Failed to initialize embedding extractor")
-        return
-
-    # Perform diarization with profiling
-    print("Starting diarization...")
-    diarization_result = perform_speaker_diarization_on_utterances(
-        audio, sample_rate, utterances, embedding_extractor, config_dict
-    )
-    print(f"Diarization completed: {len(diarization_result)} results")
-
-if __name__ == "__main__":
-    main()

requirements.txt

@@ -16,4 +16,5 @@ ffmpeg-python
 feedparser
 sherpa_onnx
 huggingface_hub
-faiss-cpu
+faiss-cpu
+memory_profiler