xref: /aosp_15_r20/external/libopus/dnn/torch/osce/test_vocoder.py (revision a58d3d2adb790c104798cd88c8a3aff4fa8b82cc)
1"""
2/* Copyright (c) 2023 Amazon
3   Written by Jan Buethe */
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 COPYRIGHT OWNER
20   OR 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
30import argparse
31
32import torch
33
34from scipy.io import wavfile
35
36from time import time
37
38
39from models import model_dict
40from utils.lpcnet_features import load_lpcnet_features
41from utils import endoscopy
42
43debug = False
44if debug:
45    args = type('dummy', (object,),
46    {
47        'input'         : 'testitems/all_0_orig.se',
48        'checkpoint'    : 'testout/checkpoints/checkpoint_epoch_5.pth',
49        'output'        : 'out.wav',
50    })()
51else:
52    parser = argparse.ArgumentParser()
53
54    parser.add_argument('input', type=str, help='path to input features')
55    parser.add_argument('checkpoint', type=str, help='checkpoint file')
56    parser.add_argument('output', type=str, help='output file')
57    parser.add_argument('--debug', action='store_true', help='enables debug output')
58
59
60    args = parser.parse_args()
61
62
63torch.set_num_threads(2)
64
65input_folder = args.input
66checkpoint_file = args.checkpoint
67
68
69output_file = args.output
70if not output_file.endswith('.wav'):
71    output_file += '.wav'
72
73checkpoint = torch.load(checkpoint_file, map_location="cpu")
74
75# check model
76if not 'name' in checkpoint['setup']['model']:
77    print(f'warning: did not find model name entry in setup, using pitchpostfilter per default')
78    model_name = 'pitchpostfilter'
79else:
80    model_name = checkpoint['setup']['model']['name']
81
82model = model_dict[model_name](*checkpoint['setup']['model']['args'], **checkpoint['setup']['model']['kwargs'])
83
84model.load_state_dict(checkpoint['state_dict'])
85
86# generate model input
87setup = checkpoint['setup']
88testdata = load_lpcnet_features(input_folder)
89features = testdata['features']
90periods = testdata['periods']
91
92if args.debug:
93    endoscopy.init()
94
95start = time()
96output = model.process(features, periods, debug=args.debug)
97elapsed = time() - start
98print(f"[timing] inference took {elapsed * 1000} ms")
99
100wavfile.write(output_file, 16000, output.cpu().numpy())
101
102if args.debug:
103    endoscopy.close()
104