1#!/usr/bin/python3 2'''Copyright (c) 2018 Mozilla 3 4 Redistribution and use in source and binary forms, with or without 5 modification, are permitted provided that the following conditions 6 are met: 7 8 - Redistributions of source code must retain the above copyright 9 notice, this list of conditions and the following disclaimer. 10 11 - Redistributions in binary form must reproduce the above copyright 12 notice, this list of conditions and the following disclaimer in the 13 documentation and/or other materials provided with the distribution. 14 15 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 16 ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 17 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 18 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR 19 CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 20 EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 21 PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 22 PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 23 LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 24 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 25 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 26''' 27import argparse 28import sys 29 30import h5py 31import numpy as np 32 33import lpcnet 34from ulaw import ulaw2lin, lin2ulaw 35 36 37parser = argparse.ArgumentParser() 38parser.add_argument('model-file', type=str, help='model weight h5 file') 39parser.add_argument('--lpc-gamma', type=float, help='LPC weighting factor. WARNING: giving an inconsistent value here will severely degrade performance', default=1) 40 41args = parser.parse_args() 42 43filename = args.model_file 44with h5py.File(filename, "r") as f: 45 units = min(f['model_weights']['gru_a']['gru_a']['recurrent_kernel:0'].shape) 46 units2 = min(f['model_weights']['gru_b']['gru_b']['recurrent_kernel:0'].shape) 47 cond_size = min(f['model_weights']['feature_dense1']['feature_dense1']['kernel:0'].shape) 48 e2e = 'rc2lpc' in f['model_weights'] 49 50 51model, enc, dec = lpcnet.new_lpcnet_model(training = False, rnn_units1=units, rnn_units2=units2, flag_e2e = e2e, cond_size=cond_size, batch_size=1) 52 53model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy']) 54#model.summary() 55 56 57feature_file = sys.argv[2] 58out_file = sys.argv[3] 59frame_size = model.frame_size 60nb_features = 36 61nb_used_features = model.nb_used_features 62 63features = np.fromfile(feature_file, dtype='float32') 64features = np.resize(features, (-1, nb_features)) 65nb_frames = 1 66feature_chunk_size = features.shape[0] 67pcm_chunk_size = frame_size*feature_chunk_size 68 69features = np.reshape(features, (nb_frames, feature_chunk_size, nb_features)) 70periods = (.1 + 50*features[:,:,18:19]+100).astype('int16') 71 72 73 74model.load_weights(filename); 75 76order = 16 77 78pcm = np.zeros((nb_frames*pcm_chunk_size, )) 79fexc = np.zeros((1, 1, 3), dtype='int16')+128 80state1 = np.zeros((1, model.rnn_units1), dtype='float32') 81state2 = np.zeros((1, model.rnn_units2), dtype='float32') 82 83mem = 0 84coef = 0.85 85 86lpc_weights = np.array([args.lpc_gamma ** (i + 1) for i in range(16)]) 87 88fout = open(out_file, 'wb') 89 90skip = order + 1 91for c in range(0, nb_frames): 92 if not e2e: 93 cfeat = enc.predict([features[c:c+1, :, :nb_used_features], periods[c:c+1, :, :]]) 94 else: 95 cfeat,lpcs = enc.predict([features[c:c+1, :, :nb_used_features], periods[c:c+1, :, :]]) 96 for fr in range(0, feature_chunk_size): 97 f = c*feature_chunk_size + fr 98 if not e2e: 99 a = features[c, fr, nb_features-order:] * lpc_weights 100 else: 101 a = lpcs[c,fr] 102 for i in range(skip, frame_size): 103 pred = -sum(a*pcm[f*frame_size + i - 1:f*frame_size + i - order-1:-1]) 104 fexc[0, 0, 1] = lin2ulaw(pred) 105 106 p, state1, state2 = dec.predict([fexc, cfeat[:, fr:fr+1, :], state1, state2]) 107 #Lower the temperature for voiced frames to reduce noisiness 108 p *= np.power(p, np.maximum(0, 1.5*features[c, fr, 19] - .5)) 109 p = p/(1e-18 + np.sum(p)) 110 #Cut off the tail of the remaining distribution 111 p = np.maximum(p-0.002, 0).astype('float64') 112 p = p/(1e-8 + np.sum(p)) 113 114 fexc[0, 0, 2] = np.argmax(np.random.multinomial(1, p[0,0,:], 1)) 115 pcm[f*frame_size + i] = pred + ulaw2lin(fexc[0, 0, 2]) 116 fexc[0, 0, 0] = lin2ulaw(pcm[f*frame_size + i]) 117 mem = coef*mem + pcm[f*frame_size + i] 118 #print(mem) 119 np.array([np.round(mem)], dtype='int16').tofile(fout) 120 skip = 0 121