MMMMichaelzhang
commented
2 years ago meldataset.py:
coding: utf-8
import os import os.path as osp import time import random import numpy as np import random import soundfile as sf
import torch from torch import nn import torch.nn.functional as F import torchaudio from torch.utils.data import DataLoader
from g2pM import G2pM
import logging logger = logging.getLogger(name) logger.setLevel(logging.DEBUG) from text_utils import TextCleaner np.random.seed(1) random.seed(1) DEFAULT_DICT_PATH = osp.join(osp.dirname(file), 'word_index_dict.txt') #'kata_dict.csv') # SPECT_PARAMS = { "n_fft": 2048, "win_length": 1200, "hop_length": 300 } MEL_PARAMS = { "n_mels": 80, }
class MelDataset(torch.utils.data.Dataset): def init(self, data_list, dict_path=DEFAULT_DICT_PATH, sr=24000 ):
spect_params = SPECT_PARAMS
mel_params = MEL_PARAMS
_data_list = [l[:-1].split('|') for l in data_list]
self.data_list = [data if len(data) == 3 else (*data, 0) for data in _data_list]
self.text_cleaner = TextCleaner(dict_path)
self.sr = sr
self.to_melspec = torchaudio.transforms.MelSpectrogram(**MEL_PARAMS)
self.mean, self.std = -4, 4
self.g2p = G2pM()
def __len__(self):
return len(self.data_list)
def __getitem__(self, idx):
data = self.data_list[idx]
wave, text_tensor, speaker_id = self._load_tensor(data)
wave_tensor = torch.from_numpy(wave).float()
mel_tensor = self.to_melspec(wave_tensor)
if (text_tensor.size(0)+1) >= (mel_tensor.size(1) // 3):
mel_tensor = F.interpolate(
mel_tensor.unsqueeze(0), size=(text_tensor.size(0)+1)*3, align_corners=False,
mode='linear').squeeze(0)
acoustic_feature = (torch.log(1e-5 + mel_tensor) - self.mean)/self.std
length_feature = acoustic_feature.size(1)
acoustic_feature = acoustic_feature[:, :(length_feature - length_feature % 2)]
return wave_tensor, acoustic_feature, text_tensor, data[0]
def _load_tensor(self, data):
wave_path, text, speaker_id = data
speaker_id = int(speaker_id)
wave, sr = sf.read(wave_path)
# phonemize the text
ps = self.g2p(text.replace('-', ' '))
if "'" in ps:
ps.remove("'")
text = self.text_cleaner(ps)
blank_index = self.text_cleaner.word_index_dictionary[" "]
text.insert(0, blank_index) # add a blank at the beginning (silence)
text.append(blank_index) # add a blank at the end (silence)
text = torch.LongTensor(text)
return wave, text, speaker_idclass Collater(object): """ Args: return_wave (bool): if true, will return the wave data along with spectrogram. """
def __init__(self, return_wave=False):
self.text_pad_index = 0
self.return_wave = return_wave
def __call__(self, batch):
batch_size = len(batch)
# sort by mel length
lengths = [b[1].shape[1] for b in batch]
batch_indexes = np.argsort(lengths)[::-1]
batch = [batch[bid] for bid in batch_indexes]
nmels = batch[0][1].size(0)
max_mel_length = max([b[1].shape[1] for b in batch])
max_text_length = max([b[2].shape[0] for b in batch])
mels = torch.zeros((batch_size, nmels, max_mel_length)).float()
texts = torch.zeros((batch_size, max_text_length)).long()
input_lengths = torch.zeros(batch_size).long()
output_lengths = torch.zeros(batch_size).long()
paths = ['' for _ in range(batch_size)]
for bid, (_, mel, text, path) in enumerate(batch):
mel_size = mel.size(1)
text_size = text.size(0)
mels[bid, :, :mel_size] = mel
texts[bid, :text_size] = text
input_lengths[bid] = text_size
output_lengths[bid] = mel_size
paths[bid] = path
assert(text_size < (mel_size//2))
if self.return_wave:
waves = [b[0] for b in batch]
return texts, input_lengths, mels, output_lengths, paths, waves
return texts, input_lengths, mels, output_lengthsdef build_dataloader(path_list, validation=False, batch_size=4, num_workers=1, device='cpu', collate_config={}, dataset_config={}):
dataset = MelDataset(path_list, **dataset_config)
collate_fn = Collater(**collate_config)
data_loader = DataLoader(dataset,
batch_size=batch_size,
shuffle=(not validation),
num_workers=num_workers,
drop_last=(not validation),
collate_fn=collate_fn,
pin_memory=(device != 'cpu'))
return data_loader
Kristopher-Chen
yl4579
Charlottecuc
superhg
[train]: 24%|██▍ | 16/66 [00:04<00:15, 3.20it/s] Traceback (most recent call last): File "/home/mike/PycharmProjects/AuxiliaryASR/train.py", line 116, in
main()
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/click/core.py", line 1130, in call
return self.main(args, kwargs)
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/click/core.py", line 1055, in main
rv = self.invoke(ctx)
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/click/core.py", line 1404, in invoke
return ctx.invoke(self.callback, ctx.params)
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/click/core.py", line 760, in invoke
return __callback(args, **kwargs)
File "/home/mike/PycharmProjects/AuxiliaryASR/train.py", line 98, in main
train_results = trainer._train_epoch()
File "/home/mike/PycharmProjects/AuxiliaryASR/trainer.py", line 186, in _train_epoch
for train_steps_per_epoch, batch in enumerate(tqdm(self.train_dataloader, desc="[train]"), 1):
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/tqdm/std.py", line 1195, in iter
for obj in iterable:
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 530, in next
data = self._next_data()
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1204, in _next_data
return self._process_data(data)
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1250, in _process_data
data.reraise()
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/torch/_utils.py", line 457, in reraise
raise exception
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/mike/anaconda3/envs/asr/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/mike/PycharmProjects/AuxiliaryASR/meldataset.py", line 60, in getitem
wave, text_tensor, speaker_id = self._load_tensor(data)
File "/home/mike/PycharmProjects/AuxiliaryASR/meldataset.py", line 78, in _load_tensor
speaker_id = int(speaker_id)
ValueError: invalid literal for int() with base 10: ''
my train_list : /media/mike/yys/data_asr/SSB00800056.wav|wo men can jia guo xu duo zhong da huo dong de biao yan|0 /media/mike/yys/data_asr/SSB00050001.wav|guang zhou nv da xue sheng deng shan shi lian si tian jing fang zhao dao yi si nv shi|0 /media/mike/yys/data_asr/SSB00050002.wav|zhun zhong ke xue gui lv de yao qiu|0 /media/mike/yys/data_asr/SSB00050003.wav|qi lu wu ren shou piao|0 ..