audio-tagging-c-api.c
2.6 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
// c-api-examples/audio-tagging-c-api.c
//
// Copyright (c) 2024 Xiaomi Corporation
// We assume you have pre-downloaded the model files for testing
// from https://github.com/k2-fsa/sherpa-onnx/releases/tag/audio-tagging-models
//
// An example is given below:
//
// clang-format off
//
// wget https://github.com/k2-fsa/sherpa-onnx/releases/download/audio-tagging-models/sherpa-onnx-zipformer-audio-tagging-2024-04-09.tar.bz2
// tar xvf sherpa-onnx-zipformer-audio-tagging-2024-04-09.tar.bz2
// rm sherpa-onnx-zipformer-audio-tagging-2024-04-09.tar.bz2
//
// clang-format on
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "sherpa-onnx/c-api/c-api.h"
int32_t main() {
SherpaOnnxAudioTaggingConfig config;
memset(&config, 0, sizeof(config));
config.model.zipformer.model =
"./sherpa-onnx-zipformer-audio-tagging-2024-04-09/model.int8.onnx";
config.model.num_threads = 1;
config.model.debug = 1;
config.model.provider = "cpu";
// clang-format off
config.labels = "./sherpa-onnx-zipformer-audio-tagging-2024-04-09/class_labels_indices.csv";
// clang-format on
const SherpaOnnxAudioTagging *tagger = SherpaOnnxCreateAudioTagging(&config);
if (!tagger) {
fprintf(stderr, "Failed to create audio tagger. Please check your config");
return -1;
}
// You can find more test waves from
// https://github.com/k2-fsa/sherpa-onnx/releases/download/audio-tagging-models/sherpa-onnx-zipformer-audio-tagging-2024-04-09.tar.bz2
const char *wav_filename =
"./sherpa-onnx-zipformer-audio-tagging-2024-04-09/test_wavs/1.wav";
const SherpaOnnxWave *wave = SherpaOnnxReadWave(wav_filename);
if (wave == NULL) {
fprintf(stderr, "Failed to read %s\n", wav_filename);
return -1;
}
const SherpaOnnxOfflineStream *stream =
SherpaOnnxAudioTaggingCreateOfflineStream(tagger);
SherpaOnnxAcceptWaveformOffline(stream, wave->sample_rate, wave->samples,
wave->num_samples);
int32_t top_k = 5;
const SherpaOnnxAudioEvent *const *results =
SherpaOnnxAudioTaggingCompute(tagger, stream, top_k);
fprintf(stderr, "--------------------------------------------------\n");
fprintf(stderr, "Index\t\tProbability\t\tEvent name\n");
fprintf(stderr, "--------------------------------------------------\n");
for (int32_t i = 0; i != top_k; ++i) {
fprintf(stderr, "%d\t\t%.3f\t\t\t%s\n", i, results[i]->prob,
results[i]->name);
}
fprintf(stderr, "--------------------------------------------------\n");
SherpaOnnxAudioTaggingFreeResults(results);
SherpaOnnxDestroyOfflineStream(stream);
SherpaOnnxFreeWave(wave);
SherpaOnnxDestroyAudioTagging(tagger);
return 0;
};