deepSpeech_input.py 文件源码

def _generate_feats_and_label_batch(filename_queue, batch_size):
    """Construct a queued batch of spectral features and transcriptions.

    Args:
      filename_queue: queue of filenames to read data from.
      batch_size: Number of utterances per batch.

    Returns:
      feats: mfccs. 4D tensor of [batch_size, height, width, 3] size.
      labels: transcripts. List of length batch_size.
      seq_lens: Sequence Lengths. List of length batch_size.
    """

    # Define how to parse the example
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    context_features = {
        "seq_len": tf.FixedLenFeature([], dtype=tf.int64),
        "labels": tf.VarLenFeature(dtype=tf.int64)
    }
    sequence_features = {
        # mfcc features are 13 dimensional
        "feats": tf.FixedLenSequenceFeature([13, ], dtype=tf.float32) 
    }

    # Parse the example (returns a dictionary of tensors)
    context_parsed, sequence_parsed = tf.parse_single_sequence_example(
        serialized=serialized_example,
        context_features=context_features,
        sequence_features=sequence_features
    )

    # Generate a batch worth of examples after bucketing
    seq_len, (feats, labels) = tf.contrib.training.bucket_by_sequence_length(
        input_length=tf.cast(context_parsed['seq_len'], tf.int32),
        tensors=[sequence_parsed['feats'], context_parsed['labels']],
        batch_size=batch_size,
        bucket_boundaries=list(range(100, 1900, 100)),
        allow_smaller_final_batch=True,
        num_threads=16,
        dynamic_pad=True)

    return feats, tf.cast(labels, tf.int32), seq_len