speech_recognizer.py 文件源码

def build_models(input_folder):
    # Initialize the variable to store all the models
    speech_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 the variables
        X = np.array([])

        # Create a list of files to be used for training
        # We will leave one file per folder for testing
        training_files = [x for x in os.listdir(subfolder) if x.endswith('.wav')][:-1]

        # Iterate through the training files and build the models
        for filename in training_files: 
            # Extract the current filepath
            filepath = os.path.join(subfolder, filename)

            # Read the audio signal from the input file
            sampling_freq, signal = wavfile.read(filepath)

            # Extract the MFCC features
            with warnings.catch_warnings():
                warnings.simplefilter('ignore')
                features_mfcc = mfcc(signal, sampling_freq)

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

        # Create the HMM model
        model = ModelHMM()

        # Train the HMM
        model.train(X)

        # Save the model for the current word
        speech_models.append((model, label))

        # Reset the variable
        model = None

    return speech_models

# Define a function to run tests on input files