(original) (raw)

import numpy as np import pandas as pd import tensorflow as tf from tensorflow.python.ops import gen_audio_ops as contrib_audio from deepspeech_training.util.text import Alphabet from ds_ctcdecoder import ctc_beam_search_decoder, Scorer ## Preprocessing + Postprocessing functions are constructed using code in DeepSpeech repository: https://github.com/mozilla/DeepSpeech audio_window_samples = 512 audio_step_samples = 320 n_input = 26 audio_sample_rate = 16000 context = 9 lm_alpha = 0.931289039105002 lm_beta = 1.1834137581510284 scorer_path = "./kenlm.scorer" beam_width = 1024 cutoff_prob = 1.0 cutoff_top_n = 300 alphabet = Alphabet("./alphabet.txt") scorer = Scorer(lm_alpha, lm_beta, scorer_path, alphabet) def audiofile_to_features(wav_filename): samples = tf.io.read_file(wav_filename) decoded = contrib_audio.decode_wav(samples, desired_channels=1) spectrogram = contrib_audio.audio_spectrogram(decoded.audio, window_size=audio_window_samples, stride=audio_step_samples, magnitude_squared=True) mfccs = contrib_audio.mfcc(spectrogram = spectrogram, sample_rate = decoded.sample_rate, dct_coefficient_count=n_input, upper_frequency_limit=audio_sample_rate/2) mfccs = tf.reshape(mfccs, [-1, n_input]) return mfccs, tf.shape(input=mfccs)[0] def create_overlapping_windows(batch_x): batch_size = tf.shape(input=batch_x)[0] window_width = 2 * context + 1 num_channels = n_input eye_filter = tf.constant(np.eye(window_width * num_channels) .reshape(window_width, num_channels, window_width * num_channels), tf.float32) # Create overlapping windows batch_x = tf.nn.conv1d(input=batch_x, filters=eye_filter, stride=1, padding='SAME') batch_x = tf.reshape(batch_x, [batch_size, -1, window_width, num_channels]) return batch_x sess = tf.Session(graph=tf.Graph()) with sess.graph.as_default() as g: path = tf.placeholder(tf.string) _features, _ = audiofile_to_features(path) _features = tf.expand_dims(_features, 0) _features = create_overlapping_windows(_features) def preprocessing(input_file_path): return _features.eval(session=sess, feed_dict={path: input_file_path}) def postprocessing(logits): logits = np.squeeze(logits) decoded = ctc_beam_search_decoder(logits, alphabet, beam_width, scorer=scorer, cutoff_prob=cutoff_prob, cutoff_top_n=cutoff_top_n) return decoded def inspect_tf_outputs(path): with open(path, 'rb') as f: serialized = f.read() gdef = tf.GraphDef() gdef.ParseFromString(serialized) with tf.Graph().as_default() as g: tf.import_graph_def(gdef, name="") output_nodes = [] for op in g.get_operations(): if op.type == "Const": continue if all([len(g.get_tensor_by_name(tensor.name).consumers()) == 0 for tensor in op.outputs]): output_nodes.append(op.name) return output_nodes def inspect_inputs(mlmodel, tfmodel): names = [] ranks = [] shapes = [] spec = mlmodel.get_spec() with open(tfmodel, 'rb') as f: serialized = f.read() gdef = tf.GraphDef() gdef.ParseFromString(serialized) with tf.Graph().as_default() as g: tf.import_graph_def(gdef, name="") for tensor in spec.description.input: name = tensor.name shape = tensor.type.multiArrayType.shape if tensor.type.multiArrayType.shapeRange: for dim, size in enumerate(tensor.type.multiArrayType.shapeRange.sizeRanges): if size.upperBound == -1: shape[dim] = -1 elif size.lowerBound < size.upperBound: shape[dim] = -1 elif size.lowerBound == size.upperBound: assert shape[dim] == size.lowerBound else: raise TypeError("Invalid shape range") coreml_shape = tuple(None if i == -1 else i for i in shape) tf_shape = tuple(g.get_tensor_by_name(name + ":0").shape.as_list()) shapes.append({"Core ML shape": coreml_shape, "TF shape": tf_shape}) names.append(name) ranks.append(len(coreml_shape)) columns = [shapes[i] for i in np.argsort(ranks)[::-1]] indices = [names[i] for i in np.argsort(ranks)[::-1]] return pd.DataFrame(columns, index= indices)