Open mmaz opened 2 years ago
uhohs = [] mswc_16khz = Path("/media/mark/hyperion/mswc/16khz_wav/en/clips") keywords = list(sorted(os.listdir(mswc_16khz))) print(len(keywords)) for keyword in tqdm.tqdm(keywords): keyword_samples = list(sorted((mswc_16khz / keyword).glob("*.wav"))) if len(keyword_samples) == 0: uhohs.append(keyword) print(len(uhohs)) >>> 24