:param languages (str): language from which you want to get html :return df (DataFrame): DataFrame that contains all audio metadata from sea

Retrieves html in text form from ROOT_URL :param urls (list): List of urls from which to retrieve html :return (list): list of HTML strin

Makes segments of mfccs and attaches them to the labels :param mfccs: list of mfccs :param labels: list of labels :return (tuple): Se

Converts list of languages into a binary class matrix :param y (list): list of languages :return (numpy array): binary class matrix

creates url from ROOT_URL and languages :param languages (list): List of languages :return (list): List of urls

Checks if self.distination_folder exists. If not, a folder called self.destination_folder is created

Create confusion matrix :param y_predicted: list of predictions :param y_test: numpy array of shape (len(y_test), number of classes). 1.'

Creates segmented MFCCs from X_train :param X_train: list of MFCCs :return: segmented mfccs

Function to filter audio files based on df columns df column options: [age,age_of_english_onset,age_sex,birth_place,english_learning_method,

Retrieves all audio files from 'language_num' column of self.audio_df If audio file already exists, move on to the next :retu

Retrieves HTML from list of hrefs and returns bio information :param hrefs (list): list of hrefs :return (DataFrame): Pandas DataFrame wi

Parse bio data from row string :param row (str): Unparsed bio string :return (list): Bio columns

Extracts href property from HTML <p> tag string :param p_tag (str): HTML string :return (str): string of link

Predict class based on MFCC samples :param MFCCs: Numpy array of MFCCs :param model: Trained model :return: Predicted class of MFCC s

Save model to file :param model: Trained model to be saved :param model_filename: Filename :return: None

Creates segments from on mfcc image. If last segments is not long enough to be length of columns divided by COL_SIZE :param mfcc (numpy array

Create train test split of DataFrame :param df (DataFrame): Pandas DataFrame of audio files to be split :param test_size (float): Percent

Trains 2D convolutional neural network :param X_train: Numpy array of mfccs :param y_train: Binary matrix based on labels :return: Tr

Initializes GetAudio class object :param destination_folder (str): Folder where audio files will be saved :param wait (float)

Get accuracy :param y_predicted: numpy array of predictions :param y_test: numpy array of actual :return: accuracy

Load wav file from disk and down-samples to RATE :param language_num (list): list of file names :return (numpy array): Down-sampled wav f

Normalize mfcc :param mfcc: :return:

:param X_train: List of segmented mfccs :param model: trained model :return: list of predictions

Predict class based on MFCC samples' probabilities :param MFCCs: Numpy array of MFCCs :param model: Trained model :return: Predicted

Searches wav form for segments of silence. If wav form values are lower than 'thresh' for 'chunk' samples, the values will be removed :param

Converts wav file to Mel Frequency Ceptral Coefficients :param wav (numpy array): Wav form :return (2d numpy array: MFCC