from torch.utils.data import Dataset


class AudioDataset(Dataset):
 def __init__(self, ...):
 """類的初始化"""
 pass

 def __getitem__(self, item):
 """每次怎么讀數(shù)據(jù)，返回數(shù)據(jù)和標簽"""
 return data, label

 def __len__(self):
 """返回整個數(shù)據(jù)集的長度"""
 return total

class AudioDataset(Dataset):
 def __init__(self, data_folder, sr=16000, dimension=8192):
 self.data_folder = data_folder
 self.sr = sr
 self.dim = dimension

 # 獲取音頻名列表
 self.wav_list = []
 for root, dirnames, filenames in os.walk(data_folder):
 for filename in fnmatch.filter(filenames, "*.wav"): # 實現(xiàn)列表特殊字符的過濾或篩選,返回符合匹配“.wav”字符列表
 self.wav_list.append(os.path.join(root, filename))

 def __getitem__(self, item):
 # 讀取一個音頻文件，返回每個音頻數(shù)據(jù)
 filename = self.wav_list[item]
 wb_wav, _ = librosa.load(filename, sr=self.sr)

 # 取 幀
 if len(wb_wav) >= self.dim:
 max_audio_start = len(wb_wav) - self.dim
 audio_start = np.random.randint(0, max_audio_start)
 wb_wav = wb_wav[audio_start: audio_start + self.dim]
 else:
 wb_wav = np.pad(wb_wav, (0, self.dim - len(wb_wav)), "constant")

 return wb_wav, filename

 def __len__(self):
 # 音頻文件的總數(shù)
 return len(self.wav_list)

Dataset= AudioDataset("./p225", sr=16000)

# 實例化AudioDataset對象
train_set = AudioDataset("./p225", sr=16000)

for i, data in enumerate(train_set):
 wb_wav, filname = data
 print(i, wb_wav.shape, filname)

 if i == 3:
 break
 # 0 (8192,) ./p225\p225_001.wav
 # 1 (8192,) ./p225\p225_002.wav
 # 2 (8192,) ./p225\p225_003.wav
 # 3 (8192,) ./p225\p225_004.wav

DataLoader(dataset, batch_size=1, shuffle=False, sampler=None, num_workers=0, collate_fn=default_collate, pin_memory=False, drop_last=False)

# 實例化AudioDataset對象
train_set = AudioDataset("./p225", sr=16000)
train_loader = DataLoader(train_set, batch_size=8, shuffle=True)

for (i, data) in enumerate(train_loader):
 wav_data, wav_name = data
 print(wav_data.shape) # torch.Size([8, 8192])
 print(i, wav_name)
 # ('./p225\\p225_293.wav', './p225\\p225_156.wav', './p225\\p225_277.wav', './p225\\p225_210.wav',
 # './p225\\p225_126.wav', './p225\\p225_021.wav', './p225\\p225_257.wav', './p225\\p225_192.wav')

import fnmatch
import os
import librosa
import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import DataLoader


class Aduio_DataLoader(Dataset):
 def __init__(self, data_folder, sr=16000, dimension=8192):
 self.data_folder = data_folder
 self.sr = sr
 self.dim = dimension

 # 獲取音頻名列表
 self.wav_list = []
 for root, dirnames, filenames in os.walk(data_folder):
  for filename in fnmatch.filter(filenames, "*.wav"): # 實現(xiàn)列表特殊字符的過濾或篩選,返回符合匹配“.wav”字符列表
  self.wav_list.append(os.path.join(root, filename))

 def __getitem__(self, item):
 # 讀取一個音頻文件，返回每個音頻數(shù)據(jù)
 filename = self.wav_list[item]
 print(filename)
 wb_wav, _ = librosa.load(filename, sr=self.sr)

 # 取 幀
 if len(wb_wav) >= self.dim:
  max_audio_start = len(wb_wav) - self.dim
  audio_start = np.random.randint(0, max_audio_start)
  wb_wav = wb_wav[audio_start: audio_start + self.dim]
 else:
  wb_wav = np.pad(wb_wav, (0, self.dim - len(wb_wav)), "constant")

 return wb_wav, filename

 def __len__(self):
 # 音頻文件的總數(shù)
 return len(self.wav_list)


train_set = Aduio_DataLoader("./p225", sr=16000)
train_loader = DataLoader(train_set, batch_size=8, shuffle=True)


for (i, data) in enumerate(train_loader):
 wav_data, wav_name = data
 print(wav_data.shape) # torch.Size([8, 8192])
 print(i, wav_name)
 # ('./p225\\p225_293.wav', './p225\\p225_156.wav', './p225\\p225_277.wav', './p225\\p225_210.wav',
 # './p225\\p225_126.wav', './p225\\p225_021.wav', './p225\\p225_257.wav', './p225\\p225_192.wav')

import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
import h5py

def load_h5(h5_path):
 # load training data
 with h5py.File(h5_path, 'r') as hf:
 print('List of arrays in input file:', hf.keys())
 X = np.array(hf.get('data'), dtype=np.float32)
 Y = np.array(hf.get('label'), dtype=np.float32)
 return X, Y


class AudioDataset(Dataset):
 """數(shù)據(jù)加載器"""
 def __init__(self, data_folder):
 self.data_folder = data_folder
 self.X, self.Y = load_h5(data_folder) # (3392, 8192, 1)

 def __getitem__(self, item):
 # 返回一個音頻數(shù)據(jù)
 X = self.X[item]
 Y = self.Y[item]

 return X, Y

 def __len__(self):
 return len(self.X)


train_set = AudioDataset("./speaker225_resample_train.h5")
train_loader = DataLoader(train_set, batch_size=64, shuffle=True, drop_last=True)


for (i, wav_data) in enumerate(train_loader):
 X, Y = wav_data
 print(i, X.shape)
 # 0 torch.Size([64, 8192, 1])
 # 1 torch.Size([64, 8192, 1])
 # ...