export model

游雁

2023-02-14 1d4ab65c8bfebaecbcb0eec0064bae9a321cad75

 funasr/datasets/large_datasets/dataset.py

@@ -1,9 +1,10 @@
import os
import random
import soundfile
import numpy
from functools import partial

import torch
import torchaudio
import torch.distributed as dist
from kaldiio import ReadHelper
from torch.utils.data import IterableDataset
@@ -117,7 +118,9 @@
                            sample_dict["key"] = key
                    elif data_type == "sound":
                        key, path = item.strip().split()
                        mat, sampling_rate = soundfile.read(path)
                        waveform, sampling_rate = torchaudio.load(path)
                        waveform = waveform.numpy()
                        mat = waveform[0]
                        sample_dict[data_name] = mat
                        sample_dict["sampling_rate"] = sampling_rate
                        if data_name == "speech":
@@ -158,9 +161,10 @@
    filter_fn = partial(filter, **filter_conf)
    dataset = FilterIterDataPipe(dataset, fn=filter_fn)

    vocab = {'vocab': dict, 'seg_dict': seg_dict}
    tokenize_fn = partial(tokenize, **vocab)
    dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)
    if "text" in data_names:
        vocab = {'vocab': dict, 'seg_dict': seg_dict}
        tokenize_fn = partial(tokenize, **vocab)
        dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)

    if shuffle:
        buffer_conf = conf.get('shuffle_conf', {})