forked from unitreerobotics/unitree_sdk2
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathg1_audio_client_example.cpp
More file actions
272 lines (225 loc) · 8.15 KB
/
g1_audio_client_example.cpp
File metadata and controls
272 lines (225 loc) · 8.15 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
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
#include <fstream>
#include <iostream>
#include <unitree/common/time/time_tool.hpp>
#include <unitree/idl/ros2/String_.hpp>
#include <unitree/robot/channel/channel_subscriber.hpp>
#include <unitree/robot/g1/audio/g1_audio_client.hpp>
#define AUDIO_FILE_PATH "../example/g1/audio/test.wav"
#define AUDIO_SUBSCRIBE_TOPIC "rt/audio_msg"
// wave reader start
struct WaveHeader {
void SeekToDataChunk(std::istream &is) {
while (is && subchunk2_id != 0x61746164) {
is.seekg(subchunk2_size, std::istream::cur);
is.read(reinterpret_cast<char *>(&subchunk2_id), sizeof(int32_t));
is.read(reinterpret_cast<char *>(&subchunk2_size), sizeof(int32_t));
}
}
int32_t chunk_id;
int32_t chunk_size;
int32_t format;
int32_t subchunk1_id;
int32_t subchunk1_size;
int16_t audio_format;
int16_t num_channels;
int32_t sample_rate;
int32_t byte_rate;
int16_t block_align;
int16_t bits_per_sample;
int32_t subchunk2_id; // a tag of this chunk
int32_t subchunk2_size; // size of subchunk2
};
static_assert(sizeof(WaveHeader) == 44);
std::vector<uint8_t> ReadWaveImpl(std::istream &is, int32_t *sampling_rate,
int8_t *channelCount, bool *is_ok) {
WaveHeader header{};
is.read(reinterpret_cast<char *>(&header.chunk_id), sizeof(header.chunk_id));
// F F I R
if (header.chunk_id != 0x46464952) {
printf("Expected chunk_id RIFF. Given: 0x%08x\n", header.chunk_id);
*is_ok = false;
return {};
}
is.read(reinterpret_cast<char *>(&header.chunk_size),
sizeof(header.chunk_size));
is.read(reinterpret_cast<char *>(&header.format), sizeof(header.format));
// E V A W
if (header.format != 0x45564157) {
printf("Expected format WAVE. Given: 0x%08x\n", header.format);
*is_ok = false;
return {};
}
is.read(reinterpret_cast<char *>(&header.subchunk1_id),
sizeof(header.subchunk1_id));
is.read(reinterpret_cast<char *>(&header.subchunk1_size),
sizeof(header.subchunk1_size));
if (header.subchunk1_id == 0x4b4e554a) {
// skip junk padding
is.seekg(header.subchunk1_size, std::istream::cur);
is.read(reinterpret_cast<char *>(&header.subchunk1_id),
sizeof(header.subchunk1_id));
is.read(reinterpret_cast<char *>(&header.subchunk1_size),
sizeof(header.subchunk1_size));
}
if (header.subchunk1_id != 0x20746d66) {
printf("Expected subchunk1_id 0x20746d66. Given: 0x%08x\n",
header.subchunk1_id);
*is_ok = false;
return {};
}
if (header.subchunk1_size != 16 &&
header.subchunk1_size != 18) { // 16 for PCM
printf("Expected subchunk1_size 16. Given: %d\n", header.subchunk1_size);
*is_ok = false;
return {};
}
is.read(reinterpret_cast<char *>(&header.audio_format),
sizeof(header.audio_format));
if (header.audio_format != 1) { // 1 for PCM
printf("Expected audio_format 1. Given: %d\n", header.audio_format);
*is_ok = false;
return {};
}
is.read(reinterpret_cast<char *>(&header.num_channels),
sizeof(header.num_channels));
*channelCount = (int8_t)header.num_channels;
is.read(reinterpret_cast<char *>(&header.sample_rate),
sizeof(header.sample_rate));
is.read(reinterpret_cast<char *>(&header.byte_rate),
sizeof(header.byte_rate));
is.read(reinterpret_cast<char *>(&header.block_align),
sizeof(header.block_align));
is.read(reinterpret_cast<char *>(&header.bits_per_sample),
sizeof(header.bits_per_sample));
if (header.byte_rate !=
(header.sample_rate * header.num_channels * header.bits_per_sample / 8)) {
printf("Incorrect byte rate: %d. Expected: %d", header.byte_rate,
(header.sample_rate * header.num_channels * header.bits_per_sample /
8));
*is_ok = false;
return {};
}
if (header.block_align !=
(header.num_channels * header.bits_per_sample / 8)) {
printf("Incorrect block align: %d. Expected: %d\n", header.block_align,
(header.num_channels * header.bits_per_sample / 8));
*is_ok = false;
return {};
}
if (header.bits_per_sample != 16) { // we support only 16 bits per sample
printf("Expected bits_per_sample 16. Given: %d\n", header.bits_per_sample);
*is_ok = false;
return {};
}
if (header.subchunk1_size == 18) {
int16_t extra_size = -1;
is.read(reinterpret_cast<char *>(&extra_size), sizeof(int16_t));
if (extra_size != 0) {
printf(
"Extra size should be 0 for wave from NAudio. Current extra size "
"%d\n",
extra_size);
*is_ok = false;
return {};
}
}
is.read(reinterpret_cast<char *>(&header.subchunk2_id),
sizeof(header.subchunk2_id));
is.read(reinterpret_cast<char *>(&header.subchunk2_size),
sizeof(header.subchunk2_size));
header.SeekToDataChunk(is);
if (!is) {
*is_ok = false;
return {};
}
*sampling_rate = header.sample_rate;
// header.subchunk2_size contains the number of bytes in the data.
// As we assume each sample contains two bytes, so it is divided by 2 here
std::vector<int16_t> samples(header.subchunk2_size / 2);
is.read(reinterpret_cast<char *>(samples.data()), header.subchunk2_size);
if (!is) {
*is_ok = false;
return {};
}
std::vector<uint8_t> ans(samples.size() * 2);
for (int32_t i = 0; i != static_cast<int32_t>(samples.size()); ++i) {
ans[i * 2] = samples[i] & 0xFF;
ans[i * 2 + 1] = (samples[i] >> 8) & 0xFF;
}
*is_ok = true;
return ans;
}
std::vector<uint8_t> ReadWave(const std::string &filename,
int32_t *sampling_rate, int8_t *channelCount,
bool *is_ok) {
std::ifstream is(filename, std::ifstream::binary);
auto samples = ReadWaveImpl(is, sampling_rate, channelCount, is_ok);
return samples;
}
// wave reader end
void asr_handler(const void *msg) {
std_msgs::msg::dds_::String_ *resMsg = (std_msgs::msg::dds_::String_ *)msg;
std::cout << "asr_handler callback" << resMsg->data() << std::endl;
}
int main(int argc, char const *argv[]) {
if (argc < 2) {
std::cout << "Usage: audio_client_example [NetWorkInterface(eth0)]"
<< std::endl;
exit(0);
}
/*
* Initilaize ChannelFactory
*/
unitree::robot::ChannelFactory::Instance()->Init(0, argv[1]);
unitree::robot::g1::AudioClient client;
client.Init();
client.SetTimeout(10.0f);
/*ASR message Example*/
unitree::robot::ChannelSubscriber<std_msgs::msg::dds_::String_> subscriber(
AUDIO_SUBSCRIBE_TOPIC);
subscriber.InitChannel(asr_handler);
/*TTS Example*/
int32_t ret;
ret = client.TtsMaker("你好。我是宇树科技的机器人G1。例程启动成功",
0); // Auto play
std::cout << "TtsMaker ret:" << ret << std::endl;
unitree::common::Sleep(5);
/*Volume Example*/
uint8_t volume;
ret = client.GetVolume(volume);
std::cout << "GetVolume ret:" << ret
<< " volume = " << std::to_string(volume) << std::endl;
ret = client.SetVolume(60);
std::cout << "SetVolume to 60% , ret:" << ret << std::endl;
/*Audio Play Example*/
int32_t sample_rate = -1;
int8_t num_channels = 0;
bool filestate = false;
std::vector<uint8_t> pcm =
ReadWave(AUDIO_FILE_PATH, &sample_rate, &num_channels, &filestate);
std::cout << "sample_rate = " << sample_rate
<< " num_channels = " << std::to_string(num_channels)
<< " filestate =" << filestate << std::endl;
if (filestate && sample_rate == 16000 && num_channels == 1) {
client.PlayStream(
"example", std::to_string(unitree::common::GetCurrentTimeMillisecond()),
pcm);
std::cout << "start play" << std::endl;
unitree::common::Sleep(3);
std::cout << "stop play" << std::endl;
ret = client.PlayStop("example");
} else {
std::cout << "audio file format error, please check!" << std::endl;
}
/*LED Control Example*/
client.LedControl(0, 255, 0);
unitree::common::Sleep(1);
client.LedControl(0, 0, 0);
unitree::common::Sleep(1);
client.LedControl(0, 0, 255);
std::cout << "AudioClient api test finish , asr start..." << std::endl;
while (1) {
sleep(1); // wait for asr message
}
return 0;
}