EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Add C++ microphone examples for audio tagging (#749)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-04-10 21:00:35 +08:00
committed by GitHub
parent f20291cadc
commit 042976ea6e
24 changed files with 707 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
sherpa-onnx/csrc/sherpa-onnx-microphone-offline.cc
View File

@@ -139,14 +139,31 @@ for a list of pre-trained models to download.
PaDeviceIndex num_devices = Pa_GetDeviceCount();
fprintf(stderr, "Num devices: %d\n", num_devices);
PaStreamParameters param;
int32_t device_index = Pa_GetDefaultInputDevice();
param.device = Pa_GetDefaultInputDevice();
if (param.device == paNoDevice) {
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 \n");
exit(EXIT_FAILURE);
}
fprintf(stderr, "Use default device: %d\n", param.device);
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);
@@ -157,12 +174,18 @@ for a list of pre-trained models to download.
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, &param, nullptr, /* &outputParameters, */
sample_rate,
mic_sample_rate,
0, // frames per buffer
paClipOff, // we won't output out of range samples
// so don't bother clipping them
@@ -195,7 +218,7 @@ for a list of pre-trained models to download.
}
auto s = recognizer.CreateStream();
s->AcceptWaveform(sample_rate, buf.data(), buf.size());
s->AcceptWaveform(mic_sample_rate, buf.data(), buf.size());
recognizer.DecodeStream(s.get());
SHERPA_ONNX_LOGE("Decoding Done! Result is:");
SHERPA_ONNX_LOGE("%s", s->GetResult().text.c_str());