1#!/usr/bin/python3 2'''Copyright (c) 2021-2022 Amazon 3 Copyright (c) 2018-2019 Mozilla 4 5 Redistribution and use in source and binary forms, with or without 6 modification, are permitted provided that the following conditions 7 are met: 8 9 - Redistributions of source code must retain the above copyright 10 notice, this list of conditions and the following disclaimer. 11 12 - Redistributions in binary form must reproduce the above copyright 13 notice, this list of conditions and the following disclaimer in the 14 documentation and/or other materials provided with the distribution. 15 16 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 17 ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 18 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 19 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR 20 CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 21 EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 22 PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 23 PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 24 LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 25 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 26 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 27''' 28 29# Train an LPCNet model 30 31import argparse 32#from plc_loader import PLCLoader 33 34parser = argparse.ArgumentParser(description='Train a PLC model') 35 36parser.add_argument('bits', metavar='<bits file>', help='binary features file (int16)') 37parser.add_argument('output', metavar='<output>', help='output features') 38parser.add_argument('--model', metavar='<model>', default='rdovae', help='PLC model python definition (without .py)') 39group1 = parser.add_mutually_exclusive_group() 40group1.add_argument('--weights', metavar='<input weights>', help='model weights') 41parser.add_argument('--cond-size', metavar='<units>', default=1024, type=int, help='number of units in conditioning network (default 1024)') 42parser.add_argument('--batch-size', metavar='<batch size>', default=1, type=int, help='batch size to use (default 128)') 43parser.add_argument('--seq-length', metavar='<sequence length>', default=1000, type=int, help='sequence length to use (default 1000)') 44 45 46args = parser.parse_args() 47 48import importlib 49rdovae = importlib.import_module(args.model) 50 51import sys 52import numpy as np 53from tensorflow.keras.optimizers import Adam 54from tensorflow.keras.callbacks import ModelCheckpoint, CSVLogger 55import tensorflow.keras.backend as K 56import h5py 57 58import tensorflow as tf 59from rdovae import pvq_quantize 60from rdovae import apply_dead_zone 61 62# Try reducing batch_size if you run out of memory on your GPU 63batch_size = args.batch_size 64 65model, encoder, decoder, qembedding = rdovae.new_rdovae_model(nb_used_features=20, nb_bits=80, batch_size=batch_size, cond_size=args.cond_size) 66model.load_weights(args.weights) 67 68lpc_order = 16 69nbits=80 70 71 72bits_file = args.bits 73sequence_size = args.seq_length 74 75# u for unquantised, load 16 bit PCM samples and convert to mu-law 76 77 78bits = np.memmap(bits_file + "-syms.f32", dtype='float32', mode='r') 79nb_sequences = len(bits)//(40*sequence_size)//batch_size*batch_size 80bits = bits[:nb_sequences*sequence_size*40] 81 82bits = np.reshape(bits, (nb_sequences, sequence_size//2, 20*4)) 83print(bits.shape) 84 85lambda_val = 0.001 * np.ones((nb_sequences, sequence_size//2, 1)) 86quant_id = np.round(3.8*np.log(lambda_val/.0002)).astype('int16') 87quant_id = quant_id[:,:,0] 88quant_embed = qembedding(quant_id) 89quant_scale = tf.math.softplus(quant_embed[:,:,:nbits]) 90dead_zone = tf.math.softplus(quant_embed[:, :, nbits : 2 * nbits]) 91 92bits = bits*quant_scale 93bits = np.round(apply_dead_zone([bits, dead_zone]).numpy()) 94bits = bits/quant_scale 95 96 97state = np.memmap(bits_file + "-state.f32", dtype='float32', mode='r') 98 99state = np.reshape(state, (nb_sequences, sequence_size//2, 24)) 100state = state[:,-1,:] 101state = pvq_quantize(state, 82) 102#state = state/(1e-15+tf.norm(state, axis=-1,keepdims=True)) 103 104print("shapes are:") 105print(bits.shape) 106print(state.shape) 107 108bits = bits[:,1::2,:] 109features = decoder.predict([bits, state], batch_size=batch_size) 110 111features.astype('float32').tofile(args.output) 112