python-3.x - 在 python 中加载 FLAC 文件，与 scipy 或 librosa 相同

Question

我想将一些 flac 声音文件输入到 keras 模型中。使用 wavfiles 我可以做到（一个音频文件使用两次的人为示例）

import scipy.io.wavfile
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.optimizers import SGD

path = 'path/to/file.wav'
_, audio = scipy.io.wavfile.read(path)
dataset = [audio, audio]
x_train = np.array(dataset)
y_train = keras.utils.to_categorical([0, 1], num_classes=2)

model = Sequential()
model.add(Dense(32, activation='relu', input_shape=x_train[0].shape))
model.add(Dense(2, activation='softmax'))
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10, batch_size=32)

我如何使用 flac 文件来执行此操作？

Answer 1

soundfile包可以加载 numpy 数组兼容格式的 flac文件

import numpy as np                                                             
import soundfile as sf                                                      
import keras                                                                
from keras.models import Sequential                                         
from keras.layers import Dense, Dropout, Activation                         
from keras.optimizers import SGD                                            

path = 'path/to/file.flac'                                                  
data, samplerate = sf.read(path)                                            
dataset = [data, data]                                                      
x_train = np.array(dataset)                                                 
y_train = keras.utils.to_categorical([0, 1], num_classes=2)                 

model = Sequential()                                                        
model.add(Dense(32, activation='relu', input_shape=x_train[0].shape))       
model.add(Dense(2, activation='softmax'))                                   
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10, batch_size=32)    

可分叉的 sscce https://www.kaggle.com/morenoh149/flac-keras-hello-world