Question

我正在使用包含隐马尔可夫模型（HMM）的Python 3.6中的语音识别器代码。由.wav个文件组成的训练数据（输入文件夹）被组织为

train
   pineapple
   apple
   banana
   orange
   kiwi
   peach
   lime

类似的模式用于test数据文件夹。

该代码从命令提示符处运行：

python Speech-Recognizer.py --input-folder train

代码粘贴在下面：

import os
import argparse

import numpy as np
from scipy.io import wavfile
from hmmlearn import hmm
from python_speech_features import mfcc

# Function to parse input arguments
def build_arg_parser():
    parser = argparse.ArgumentParser(description='Trains the HMM classifier')
    parser.add_argument("--input-folder", dest="input_folder", required=True,
                        help="Input folder containing the audio files in subfolders")
    return parser


# Class to handle all HMM related processing
class HMMTrainer(object):
    def __init__(self, model_name='GaussianHMM', n_components=4, cov_type='diag', n_iter=1000):
        self.model_name = model_name
        self.n_components = n_components
        self.cov_type = cov_type
        self.n_iter = n_iter
        self.models = []

        if self.model_name == 'GaussianHMM':
            self.model = hmm.GaussianHMM(n_components=self.n_components,
                                         covariance_type=self.cov_type, n_iter=self.n_iter)
        else:
            raise TypeError('Invalid model type')

    # X is a 2D numpy array where each row is 13D
    def train(self, X):
        np.seterr(all='ignore')
        self.models.append(self.model.fit(X))

    # Run the model on input data
    def get_score(self, input_data):
        return self.model.score(input_data)


if __name__ == '__main__':
    args = build_arg_parser().parse_args()
    input_folder = args.input_folder

    hmm_models = []

    # Parse the input directory
    for dirname in os.listdir(input_folder):
        # Get the name of the subfolder
        subfolder = os.path.join(input_folder, dirname)

        if not os.path.isdir(subfolder):
            continue

        # Extract the label
        label = subfolder[subfolder.rfind('/') + 1:]

        # Initialize variables
        X = np.array([])
        y_words = []

        # Iterate through the audio files (leaving 1 file for testing in each class)
        for filename in [x for x in os.listdir(subfolder) if x.endswith('.wav')][:-1]:
            # Read the input file
            filepath = os.path.join(subfolder, filename)
            sampling_freq, audio = wavfile.read(filepath)

            # Extract MFCC features
            mfcc_features = mfcc(audio, sampling_freq)

            # Append to the variable X
            if len(X) == 0:
                X = mfcc_features
            else:
                X = np.append(X, mfcc_features, axis=0)

            # Append the label
            y_words.append(label)

        print('X.shape =', X.shape)
        # Train and save HMM model
        hmm_trainer = HMMTrainer()
        hmm_trainer.train(X)
        hmm_models.append((hmm_trainer, label))
        hmm_trainer = None

    # Test files
    input_files = [
        'test/pineapple/pineapple15.wav',
        'test/orange/orange15.wav',
        'test/apple/apple15.wav',
        'test/kiwi/kiwi15.wav'
    ]

    # Classify input data
    for input_file in input_files:
        # Read input file
        sampling_freq, audio = wavfile.read(input_file)

        # Extract MFCC features
        mfcc_features = mfcc(audio, sampling_freq)

        # Define variables
        max_score = None
        output_label = None

        # Iterate through all HMM models and pick
        # the one with the highest score
        for item in hmm_models:
            hmm_model, label = item
            score = hmm_model.get_score(mfcc_features)
            if score > max_score:
                max_score = score
                output_label = label

        # Print the output
        print("\nTrue:", input_file[input_file.find('/') + 1:input_file.rfind('/')])
        print("Predicted:", output_label)

运行上述代码时出现以下错误：

Traceback (most recent call last):
  File "Speech-Recognizer.py", line 113, in <module>
    if score > max_score:
TypeError: '>' not supported between instances of 'float' and 'NoneType'

Answer 1

        max_score = None
...
            if score > max_score:

您正在尝试将浮点数与“无”进行比较。

max_score = 0而不是max_score = None怎么样？

Answer 2

问这个问题已经有一段时间了，但是我想找到了解决方案，因为我也遇到了这个问题。此特定代码摘自Prateek Joshi的Python ML（2.7）书。由于当今许多人使用3.x，因此在我们的环境中，作者的代码可能无法正常工作。我看到您已经更改了库和 print（）函数的名称，但是要使代码完全起作用，您应该尝试：

# Define variables
    max_score = -np.inf
    output_label = None

然后它应该可以工作。实际上，您无法将float与None进行比较，但是使用np.inf可以解决此问题，并且HMM可以正常工作。在macOS Mojave上的PyCharm 2018.3.2中进行了测试。

Python语音识别器TypeError：“ float”和“ NoneType”的实例之间不支持“>”

2 个答案: