maui.utils.segment_audio_files¶

maui.utils.segment_audio_files(df, min_duration, output_dir, file_path_col, datetime_col)[source]¶

Segment audio files based on a minimum duration and create new DataFrame entries.

Return type:

DataFrame

Parameters:

dfpandas.DataFrame: DataFrame containing the audio file paths and timestamps.
min_durationfloat: The minimum duration in seconds for each audio segment.
output_dirstr: Directory where the segmented audio files will be saved.
file_path_colstr: Column name for the audio file paths in the DataFrame.
datetime_colstr: Column name for the start time of the audio files in the DataFrame.

Returns:

pandas.DataFrame: A DataFrame with new entries for each audio segment, including file paths and start/end times.

Examples

>>> from maui import samples, utils
>>> df = samples.get_audio_sample(dataset="leec")
>>> df["dt"] = pd.to_datetime(df["timestamp_init"]).dt.date
>>> df = df.iloc[0:1]
>>> segmented_df = utils.segment_audio_files(df, 0.2, './outputs', 'file_path', 'timestamp_init')