sherpa-onnx-microphone-offline-audio-tagging.cc
6.6 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
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
// sherpa-onnx/csrc/sherpa-onnx-microphone-offline-audio-tagging.cc
//
// Copyright (c) 2024 Xiaomi Corporation
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <algorithm>
#include <cctype> // std::tolower
#include <mutex> // NOLINT
#include <thread> // NOLINT
#include "portaudio.h" // NOLINT
#include "sherpa-onnx/csrc/audio-tagging.h"
#include "sherpa-onnx/csrc/macros.h"
#include "sherpa-onnx/csrc/microphone.h"
enum class State {
kIdle,
kRecording,
kDecoding,
};
State state = State::kIdle;
// true to stop the program and exit
bool stop = false;
std::vector<float> samples;
std::mutex samples_mutex;
static void DetectKeyPress() {
SHERPA_ONNX_LOGE("Press Enter to start");
int32_t key;
while (!stop && (key = getchar())) {
if (key != 0x0a) {
continue;
}
switch (state) {
case State::kIdle:
SHERPA_ONNX_LOGE("Start recording. Press Enter to stop recording");
state = State::kRecording;
{
std::lock_guard<std::mutex> lock(samples_mutex);
samples.clear();
}
break;
case State::kRecording:
SHERPA_ONNX_LOGE("Stop recording. Decoding ...");
state = State::kDecoding;
break;
case State::kDecoding:
break;
}
}
}
static int32_t RecordCallback(const void *input_buffer,
void * /*output_buffer*/,
unsigned long frames_per_buffer, // NOLINT
const PaStreamCallbackTimeInfo * /*time_info*/,
PaStreamCallbackFlags /*status_flags*/,
void *user_data) {
std::lock_guard<std::mutex> lock(samples_mutex);
auto p = reinterpret_cast<const float *>(input_buffer);
samples.insert(samples.end(), p, p + frames_per_buffer);
return stop ? paComplete : paContinue;
}
static void Handler(int32_t sig) {
stop = true;
fprintf(stderr, "\nCaught Ctrl + C. Press Enter to exit\n");
}
int32_t main(int32_t argc, char *argv[]) {
signal(SIGINT, Handler);
const char *kUsageMessage = R"usage(
Audio tagging from microphone.
Usage:
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
./bin/sherpa-onnx-microphone-offline-audio-tagging \
--zipformer-model=./sherpa-onnx-zipformer-audio-tagging-2024-04-09/model.onnx \
--labels=./sherpa-onnx-zipformer-audio-tagging-2024-04-09/class_labels_indices.csv
Please see
https://github.com/k2-fsa/sherpa-onnx/releases/tag/audio-tagging-models
for more models.
)usage";
sherpa_onnx::ParseOptions po(kUsageMessage);
sherpa_onnx::AudioTaggingConfig config;
config.Register(&po);
po.Read(argc, argv);
if (po.NumArgs() != 0) {
fprintf(stderr, "\nThis program does not support positional arguments\n\n");
po.PrintUsage();
exit(EXIT_FAILURE);
}
fprintf(stderr, "%s\n", config.ToString().c_str());
if (!config.Validate()) {
fprintf(stderr, "Errors in config!\n");
return -1;
}
SHERPA_ONNX_LOGE("Creating audio tagger ...");
sherpa_onnx::AudioTagging tagger(config);
SHERPA_ONNX_LOGE("Audio tagger created created!");
sherpa_onnx::Microphone mic;
PaDeviceIndex num_devices = Pa_GetDeviceCount();
fprintf(stderr, "Num devices: %d\n", num_devices);
int32_t device_index = Pa_GetDefaultInputDevice();
if (device_index == paNoDevice) {
fprintf(stderr, "No default input device found\n");
fprintf(stderr, "If you are using Linux, please switch to \n");
fprintf(stderr, " ./bin/sherpa-onnx-alsa-offline-audio-tagging \n");
exit(EXIT_FAILURE);
}
const char *pDeviceIndex = std::getenv("SHERPA_ONNX_MIC_DEVICE");
if (pDeviceIndex) {
fprintf(stderr, "Use specified device: %s\n", pDeviceIndex);
device_index = atoi(pDeviceIndex);
}
for (int32_t i = 0; i != num_devices; ++i) {
const PaDeviceInfo *info = Pa_GetDeviceInfo(i);
fprintf(stderr, " %s %d %s\n", (i == device_index) ? "*" : " ", i,
info->name);
}
PaStreamParameters param;
param.device = device_index;
fprintf(stderr, "Use device: %d\n", param.device);
const PaDeviceInfo *info = Pa_GetDeviceInfo(param.device);
fprintf(stderr, " Name: %s\n", info->name);
fprintf(stderr, " Max input channels: %d\n", info->maxInputChannels);
param.channelCount = 1;
param.sampleFormat = paFloat32;
param.suggestedLatency = info->defaultLowInputLatency;
param.hostApiSpecificStreamInfo = nullptr;
float mic_sample_rate = 16000;
const char *pSampleRateStr = std::getenv("SHERPA_ONNX_MIC_SAMPLE_RATE");
if (pSampleRateStr) {
fprintf(stderr, "Use sample rate %f for mic\n", mic_sample_rate);
mic_sample_rate = atof(pSampleRateStr);
}
float sample_rate = 16000;
PaStream *stream;
PaError err =
Pa_OpenStream(&stream, ¶m, nullptr, /* &outputParameters, */
mic_sample_rate,
0, // frames per buffer
paClipOff, // we won't output out of range samples
// so don't bother clipping them
RecordCallback, nullptr);
if (err != paNoError) {
fprintf(stderr, "portaudio error: %s\n", Pa_GetErrorText(err));
exit(EXIT_FAILURE);
}
err = Pa_StartStream(stream);
fprintf(stderr, "Started\n");
if (err != paNoError) {
fprintf(stderr, "portaudio error: %s\n", Pa_GetErrorText(err));
exit(EXIT_FAILURE);
}
std::thread t(DetectKeyPress);
while (!stop) {
switch (state) {
case State::kIdle:
break;
case State::kRecording:
break;
case State::kDecoding: {
std::vector<float> buf;
{
std::lock_guard<std::mutex> lock(samples_mutex);
buf = std::move(samples);
}
SHERPA_ONNX_LOGE("Computing...");
auto s = tagger.CreateStream();
s->AcceptWaveform(mic_sample_rate, buf.data(), buf.size());
auto results = tagger.Compute(s.get());
SHERPA_ONNX_LOGE("Result is:");
int32_t i = 0;
std::ostringstream os;
for (const auto &event : results) {
os << i << ": " << event.ToString() << "\n";
i += 1;
}
SHERPA_ONNX_LOGE("\n%s\n", os.str().c_str());
state = State::kIdle;
SHERPA_ONNX_LOGE("Press Enter to start");
break;
}
}
Pa_Sleep(20); // sleep for 20ms
}
t.join();
err = Pa_CloseStream(stream);
if (err != paNoError) {
fprintf(stderr, "portaudio error: %s\n", Pa_GetErrorText(err));
exit(EXIT_FAILURE);
}
return 0;
}