aishell example

游雁

2024-02-19 94de39dde2e616a01683c518023d0fab72b4e103

 funasr/utils/prepare_data.py

@@ -5,6 +5,7 @@

import kaldiio
import numpy as np
import librosa
import torch.distributed as dist
import torchaudio

@@ -42,7 +43,11 @@


def wav2num_frame(wav_path, frontend_conf):
    waveform, sampling_rate = torchaudio.load(wav_path)
    try:
        waveform, sampling_rate = torchaudio.load(wav_path)
    except:
        waveform, sampling_rate = librosa.load(wav_path)
        waveform = np.expand_dims(waveform, axis=0)
    n_frames = (waveform.shape[1] * 1000.0) / (sampling_rate * frontend_conf["frame_shift"] * frontend_conf["lfr_n"])
    feature_dim = frontend_conf["n_mels"] * frontend_conf["lfr_m"]
    return n_frames, feature_dim
@@ -82,6 +87,7 @@
                sample_name, feature_path = line.strip().split()
                feature = kaldiio.load_mat(feature_path)
                n_frames, feature_dim = feature.shape
                write_flag = True
                if n_frames > 0 and length_min > 0:
                    write_flag = n_frames >= length_min
                if n_frames > 0 and length_max > 0:
@@ -185,18 +191,46 @@
        for i in range(nj):
            path = ""
            for file_name in file_names:
                path = path + os.path.join(split_path, str(i + 1), file_name)
                path = path + " " + os.path.join(split_path, str(i + 1), file_name)
            f_data.write(path + "\n")


def prepare_data(args, distributed_option):
    data_names = args.dataset_conf.get("data_names", "speech,text").split(",")
    data_types = args.dataset_conf.get("data_types", "sound,text").split(",")
    file_names = args.data_file_names.split(",")
    batch_type = args.dataset_conf["batch_conf"]["batch_type"]
    print("data_names: {}, data_types: {}, file_names: {}".format(data_names, data_types, file_names))
    assert len(data_names) == len(data_types) == len(file_names)
    if args.dataset_type == "small":
        args.train_shape_file = [os.path.join(args.data_dir, args.train_set, "{}_shape".format(data_names[0]))]
        args.valid_shape_file = [os.path.join(args.data_dir, args.valid_set, "{}_shape".format(data_names[0]))]
        args.train_data_path_and_name_and_type, args.valid_data_path_and_name_and_type = [], []
        for file_name, data_name, data_type in zip(file_names, data_names, data_types):
            args.train_data_path_and_name_and_type.append(
                ["{}/{}/{}".format(args.data_dir, args.train_set, file_name), data_name, data_type])
            args.valid_data_path_and_name_and_type.append(
                ["{}/{}/{}".format(args.data_dir, args.valid_set, file_name), data_name, data_type])
        if os.path.exists(args.train_shape_file[0]):
            assert os.path.exists(args.valid_shape_file[0])
            print('shape file for small dataset already exists.')
            return
    else:
        concat_data_name = "_".join(data_names)
        args.train_data_file = os.path.join(args.data_dir, args.train_set, "{}_data.list".format(concat_data_name))
        args.valid_data_file = os.path.join(args.data_dir, args.valid_set, "{}_data.list".format(concat_data_name))
        if os.path.exists(args.train_data_file):
            assert os.path.exists(args.valid_data_file)
            print('data list for large dataset already exists.')
            return

    distributed = distributed_option.distributed
    if not distributed or distributed_option.dist_rank == 0:
        if hasattr(args, "filter_input") and args.filter_input:
            filter_wav_text(args.data_dir, args.train_set)
            filter_wav_text(args.data_dir, args.valid_set)

        if args.dataset_type == "small":
        if args.dataset_type == "small" and batch_type != "unsorted":
            calc_shape(args, args.train_set)
            calc_shape(args, args.valid_set)

@@ -204,22 +238,5 @@
            generate_data_list(args, args.data_dir, args.train_set)
            generate_data_list(args, args.data_dir, args.valid_set)

    data_names = args.dataset_conf.get("data_names", "speech,text").split(",")
    data_types = args.dataset_conf.get("data_types", "sound,text").split(",")
    file_names = args.data_file_names.split(",")
    assert len(data_names) == len(data_types) == len(file_names)
    if args.dataset_type == "small":
        args.train_shape_file = [os.path.join(args.data_dir, args.train_set, "{}_shape".format(data_names[0]))]
        args.valid_shape_file = [os.path.join(args.data_dir, args.valid_set, "{}}_shape".format(data_names[0]))]
        args.train_data_path_and_name_and_type, args.valid_data_path_and_name_and_type = [], []
        for file_name, data_name, data_type in zip(file_names, data_names, data_types):
            args.train_data_path_and_name_and_type.append(
                ["{}/{}/{}".format(args.data_dir, args.train_set, file_name), data_name, data_type])
            args.valid_data_path_and_name_and_type.append(
                ["{}/{}/{}".format(args.data_dir, args.valid_set, file_name), data_name, data_type])
    else:
        concat_data_name = "_".join(data_names)
        args.train_data_file = os.path.join(args.data_dir, args.train_set, "{}_data.list".format(concat_data_name))
        args.valid_data_file = os.path.join(args.data_dir, args.valid_set, "{}_data.list".format(concat_data_name))
    if distributed:
        dist.barrier()