funasr pages

游雁

2023-11-16 4ace5a95b052d338947fc88809a440ccd55cf6b4

 funasr/datasets/large_datasets/dataset.py

@@ -6,6 +6,8 @@
import torch
import torch.distributed as dist
import torchaudio
import numpy as np
import soundfile
from kaldiio import ReadHelper
from torch.utils.data import IterableDataset

@@ -105,8 +107,8 @@
                if data_type == "kaldi_ark":
                    ark_reader = ReadHelper('ark:{}'.format(data_file))
                    reader_list.append(ark_reader)
                elif data_type == "text" or data_type == "sound":
                    text_reader = open(data_file, "r")
                elif data_type == "text" or data_type == "sound" or data_type == 'text_hotword':
                    text_reader = open(data_file, "r", encoding="utf-8")
                    reader_list.append(text_reader)
                elif data_type == "none":
                    continue
@@ -123,7 +125,14 @@
                            sample_dict["key"] = key
                    elif data_type == "sound":
                        key, path = item.strip().split()
                        waveform, sampling_rate = torchaudio.load(path)
                        try:
                            waveform, sampling_rate = torchaudio.load(path)
                        except:
                            waveform, sampling_rate = soundfile.read(path, dtype='float32')
                            if waveform.ndim == 2:
                                waveform = waveform[:, 0]
                            waveform = np.expand_dims(waveform, axis=0)
                            waveform = torch.tensor(waveform)
                        if self.frontend_conf is not None:
                            if sampling_rate != self.frontend_conf["fs"]:
                                waveform = torchaudio.transforms.Resample(orig_freq=sampling_rate,
@@ -135,11 +144,25 @@
                            speed = random.choice(self.speed_perturb)
                            if speed != 1.0:
                                mat, _ = torchaudio.sox_effects.apply_effects_tensor(
                                    mat, sampling_rate, [['speed', str(speed)], ['rate', str(sampling_rate)]])
                                    torch.tensor(mat).view(1, -1), sampling_rate, [['speed', str(speed)], ['rate', str(sampling_rate)]])
                                mat = mat.view(-1).numpy()
                        sample_dict[data_name] = mat
                        sample_dict["sampling_rate"] = sampling_rate
                        if data_name == "speech":
                            sample_dict["key"] = key
                    elif data_type == "text_hotword":
                        text = item
                        segs = text.strip().split()
                        sample_dict[data_name] = segs[1:]
                        if "key" not in sample_dict:
                            sample_dict["key"] = segs[0]
                        sample_dict['hw_tag'] = 1
                    elif data_type == "text_nospace":
                        text = item
                        segs = text.strip().split(maxsplit=1)
                        sample_dict[data_name] = [x for x in segs[1]]
                        if "key" not in sample_dict:
                            sample_dict["key"] = segs[0]
                    else:
                        text = item
                        segs = text.strip().split()
@@ -177,17 +200,43 @@
    shuffle = conf.get('shuffle', True)
    data_names = conf.get("data_names", "speech,text")
    data_types = conf.get("data_types", "kaldi_ark,text")
    dataset = AudioDataset(scp_lists, data_names, data_types, frontend_conf=frontend_conf, shuffle=shuffle,
                           speed_perturb=speed_perturb, mode=mode)

    pre_hwfile = conf.get("pre_hwlist", None)
    # pre_prob = conf.get("pre_prob", 0)  # unused yet
    if pre_hwfile is not None:
        pre_hwlist = []
        with open(pre_hwfile, 'r', encoding="utf-8") as fin:
            for line in fin.readlines():
                pre_hwlist.append(line.strip())
    else:
        pre_hwlist = None

    hw_config = {"sample_rate": conf.get("sample_rate", 0.6),
                 "double_rate": conf.get("double_rate", 0.1),
                 "hotword_min_length": conf.get("hotword_min_length", 2),
                 "hotword_max_length": conf.get("hotword_max_length", 8),
                 "pre_prob": conf.get("pre_prob", 0.0),
                 "pre_hwlist": pre_hwlist}

    

    dataset = AudioDataset(scp_lists, 
                           data_names, 
                           data_types, 
                           frontend_conf=frontend_conf, 
                           shuffle=shuffle,
                           speed_perturb=speed_perturb,
                           mode=mode, 
                           )

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

    filter_conf = conf.get('filter_conf', {})
    filter_fn = partial(filter, **filter_conf)
    dataset = FilterIterDataPipe(dataset, fn=filter_fn)

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

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