update repo

嘉渊

2023-05-15 89bf7f681c8d8a615f2b5c4d2275a86963c9868c

 funasr/utils/prepare_data.py

@@ -27,7 +27,7 @@
        parts = line.strip().split()
        if len(parts) < 2:
            continue
        text_dict[parts[0]] = " ".join(parts[1:]).lower()
        text_dict[parts[0]] = " ".join(parts[1:])
    filter_count = 0
    with open(wav_file, "w") as f_wav, open(text_file, "w") as f_text:
        for sample_name, wav_path in wav_dict.items():
@@ -70,7 +70,7 @@
                f.flush()


def calc_shape(args, dataset, nj=32):
def calc_shape(args, dataset, nj=64):
    shape_path = os.path.join(args.data_dir, dataset, "speech_shape")
    if os.path.exists(shape_path):
        logging.info('Shape file for small dataset already exists.')
@@ -90,7 +90,7 @@
    start = 0
    for i in range(nj):
        end = start + num_job_lines
        file = os.path.join(shape_path, "wav.scp.{}".format(str(i + 1)))
        file = os.path.join(split_shape_path, "wav.scp.{}".format(str(i + 1)))
        with open(file, "w") as f:
            if i == nj - 1:
                f.writelines(lines[start:])
@@ -115,7 +115,7 @@
    logging.info('Generating shape files done.')


def generate_data_list(data_dir, dataset, nj=32):
def generate_data_list(data_dir, dataset, nj=64):
    list_file = os.path.join(data_dir, dataset, "data.list")
    if os.path.exists(list_file):
        logging.info('Data list for large dataset already exists.')
@@ -181,6 +181,11 @@
            ["{}/{}/wav.scp".format(args.data_dir, args.valid_set), data_names[0], data_types[0]],
            ["{}/{}/text".format(args.data_dir, args.valid_set), data_names[1], data_types[1]]
        ]
        if args.embed_path is not None:
            args.train_data_path_and_name_and_type.append(
                [os.path.join(args.embed_path, "embeds", args.train_set, "embeds.scp"), "embed", "kaldi_ark"])
            args.valid_data_path_and_name_and_type.append(
                [os.path.join(args.embed_path, "embeds", args.valid_set, "embeds.scp"), "embed", "kaldi_ark"])
    else:
        args.train_data_file = os.path.join(args.data_dir, args.train_set, "data.list")
        args.valid_data_file = os.path.join(args.data_dir, args.valid_set, "data.list")