import argparse import functools import itertools from mvector.predict import MVectorPredictor from mvector.utils.utils import add_arguments, print_arguments from mvector.data_utils.audio import AudioSegment parser = argparse.ArgumentParser(description=__doc__) add_arg = functools.partial(add_arguments, argparser=parser) add_arg('configs', str, 'configs/ecapa_tdnn.yml', '配置文件') add_arg('use_gpu', bool, True, '是否使用GPU预测') add_arg('audio_path1', str, 'dataset/source/王翔/wx1_5.wav', '预测第一个音频') add_arg('audio_path2', str, 'dataset/source/刘云杰/lyj_no_5.wav', '预测第二个音频') add_arg('threshold', float, 0.7, '判断是否为同一个人的阈值') add_arg('model_path', str, 'models/test_model', '导出的预测模型文件路径') args = parser.parse_args() # print_arguments(args=args) # 获取识别器 predictor = MVectorPredictor(configs=args.configs, model_path=args.model_path, use_gpu=args.use_gpu) def load_audio_paths(file_path): with open(file_path, 'r',encoding='utf-8') as file: return [line.strip() for line in file if line.strip()] def compare_audio_files(audio_paths, threshold): # itertools.combinations 生成所有可能的两两组合,无重复 for audio1, audio2 in itertools.combinations(audio_paths, 2): dist = predictor.contrast(audio1, audio2) if dist > threshold: print(f"{audio1} 和 {audio2} 为同一个人,相似度为:{dist}") # else: # print(f"{audio1} 和 {audio2} 不是同一个人,相似度为:{dist}") file_path = 'dataset/ces.txt' # 假设音频路径存储在此文件中 # 执行比对 audio_paths = load_audio_paths(file_path) compare_audio_files(audio_paths, args.threshold) # # AudioSegment.silent_semoval(args.audio_path1, args.audio_path1) # # AudioSegment.silent_semoval(args.audio_path2, args.audio_path2) # dist = predictor.contrast(args.audio_path1, args.audio_path2) # if dist > args.threshold: # print(f"{args.audio_path1} 和 {args.audio_path2} 为同一个人,相似度为:{dist}") # else: # print(f"{args.audio_path1} 和 {args.audio_path2} 不是同一个人,相似度为:{dist}")