data_loader.py 文件源码

def __init__(self, audio_conf, manifest_filepath, labels, normalize=False, augment=False):
        """
        Dataset that loads tensors via a csv containing file paths to audio files and transcripts separated by
        a comma. Each new line is a different sample. Example below:

        /path/to/audio.wav,/path/to/audio.txt
        ...

        :param audio_conf: Dictionary containing the sample rate, window and the window length/stride in seconds
        :param manifest_filepath: Path to manifest csv as describe above
        :param labels: String containing all the possible characters to map to
        :param normalize: Apply standard mean and deviation normalization to audio tensor
        :param augment(default False):  Apply random tempo and gain perturbations
        """
        with open(manifest_filepath) as f:
            ids = f.readlines()
        ids = [x.strip().split(',') for x in ids]
        self.ids = ids
        self.size = len(ids)
        self.labels_map = dict([(labels[i], i) for i in range(len(labels))])
        super(SpectrogramDataset, self).__init__(audio_conf, normalize, augment)