INNER CODE UNIT · Python

find_transcript_files

flashlight/wav2letter · data/librispeech/utils.py:16

def find_transcript_files(dir):
    files = []
    for dirpath, _, filenames in os.walk(dir):
        for filename in filenames:
            if filename.endswith(".trans.txt"):
                files.append(os.path.join(dirpath, filename))
    return files


def parse_speakers_gender(spk_file):
    ret = {}
    with open(spk_file, "r") as f:
        for line in f:
            if line.startswith(";"):
                continue
            sample_id, gen, _ = line.split("|", 2)
            ret[sample_id.strip()] = gen.strip()
    return ret

View source record →