Merge pull request #165 from alibaba-damo-academy/dev_cmz

zhifu gao

2023-02-28 a016617c7ec98ab9c7475ff7d3b6150b98d5beeb

 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
@@ -13,6 +14,7 @@
from funasr.datasets.large_datasets.datapipes.map import MapperIterDataPipe
from funasr.datasets.large_datasets.utils.filter import filter
from funasr.datasets.large_datasets.utils.padding import padding
from funasr.datasets.large_datasets.utils.clipping import clipping
from funasr.datasets.large_datasets.utils.tokenize import tokenize


@@ -101,6 +103,8 @@
                elif data_type == "text" or data_type == "sound":
                    text_reader = open(data_file, "r")
                    reader_list.append(text_reader)
                elif data_type == "none":
                    continue
                else:
                    raise TypeError("Data type {} is not supported".format(data_type))

@@ -114,21 +118,26 @@
                            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":
                            sample_dict["key"] = key
                    else:
                        text = item
                        sample_dict[data_name] = text.strip().split()[1:]
                        segs = text.strip().split()
                        sample_dict[data_name] = segs[1:]
                        if "key" not in sample_dict:
                            sample_dict["key"] = segs[0]
                yield sample_dict

            self.close_reader(reader_list)


def len_fn_example(data):
    return len(data)
    return 1


def len_fn_token(data):
@@ -142,8 +151,10 @@
def Dataset(data_list_file,
            dict,
            seg_dict,
            punc_dict,
            conf,
            mode="train"):
            mode="train",
            batch_mode="padding"):
    scp_lists = read_lists(data_list_file)
    shuffle = conf.get('shuffle', True)
    data_names = conf.get("data_names", "speech,text")
@@ -154,9 +165,10 @@
    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, 'punc_dict': punc_dict}
        tokenize_fn = partial(tokenize, **vocab)
        dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)

    if shuffle:
        buffer_conf = conf.get('shuffle_conf', {})
@@ -180,8 +192,13 @@
                                             batch_size=batch_size,
                                             len_fn=len_fn,
                                             buffer_size=buffer_size,
                                             sort_size=sort_size)
                                             sort_size=sort_size,
                                             batch_mode=batch_mode)

    dataset = MapperIterDataPipe(dataset, fn=padding)
    int_pad_value = conf.get("int_pad_value", -1)
    float_pad_value = conf.get("float_pad_value", 0.0)
    padding_conf = {"int_pad_value": int_pad_value, "float_pad_value": float_pad_value}
    padding_fn = partial(padding, **padding_conf)
    dataset = MapperIterDataPipe(dataset, fn=padding_fn if batch_mode == "padding" else clipping)

    return dataset