Audio_DQM

This is the class for computing the audio DQM.

class QPrism.Audio.DQM.Audio_DQM

Bases: object

RMS(path: str)

Compute the RMS value of the audio. This can be used to distinguish audios that are louder from each other.

Returns the root mean squared value of the audio file(s). Returns a dict matching the input audio files to their RMS value if the input path is a folder.

pathstr

A path to a folder or a file.

observation_duration(path: str)

Get the length of the audio

This functions calls the audio_length function and gives the length for both a folder of audios or a single audio file.

Returns the length of the input audio if the input path is a file. Returns a dict matching the input audio files to their length if the input path is a folder.

pathstr

A path to a folder or a file.

sampling_rate(path: str)

Get the sample rate of the audio

This functions calls the sample_rate function and gives the bit rate for both a folder of audios or a single audio file.

Returns the sample rate of the input audio if the input path is a file. Returns a dict matching the input audio files to their sample rate if the input path is a folder.

pathstr

A path to a folder or a file.

save_csv(path: str, output_path: str)

Creates a csv file consists of all the audio metrics.

Saves the csv file to output_path.

pathstr

A path to single audio file or folder

output_pathstr

path to the output csv file

voice_classification(path: str)

Get a list of all the sounds in an audio

This function identifies all the prominent sounds inside the audio

Returns a list of prominent sounds in the input audio if the input path is a file. Returns a dict matching the input audio files to their list of prominent sounds if the input path is a folder.

pathstr

A path to a folder or a file.