131 lines
3.6 KiB
C++
131 lines
3.6 KiB
C++
// sherpa-onnx/csrc/sherpa-onnx-keyword-spotter-microphone.cc
|
|
//
|
|
// Copyright (c) 2024 Xiaomi Corporation
|
|
|
|
#include <signal.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
|
|
#include <algorithm>
|
|
|
|
#include "portaudio.h" // NOLINT
|
|
#include "sherpa-onnx/csrc/display.h"
|
|
#include "sherpa-onnx/csrc/keyword-spotter.h"
|
|
#include "sherpa-onnx/csrc/microphone.h"
|
|
|
|
bool stop = false;
|
|
float mic_sample_rate = 16000;
|
|
|
|
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) {
|
|
auto stream = reinterpret_cast<sherpa_onnx::OnlineStream *>(user_data);
|
|
|
|
stream->AcceptWaveform(mic_sample_rate,
|
|
reinterpret_cast<const float *>(input_buffer),
|
|
frames_per_buffer);
|
|
|
|
return stop ? paComplete : paContinue;
|
|
}
|
|
|
|
static void Handler(int32_t /*sig*/) {
|
|
stop = true;
|
|
fprintf(stderr, "\nCaught Ctrl + C. Exiting...\n");
|
|
}
|
|
|
|
int32_t main(int32_t argc, char *argv[]) {
|
|
signal(SIGINT, Handler);
|
|
|
|
const char *kUsageMessage = R"usage(
|
|
This program uses streaming models with microphone for keyword spotting.
|
|
Usage:
|
|
|
|
./bin/sherpa-onnx-keyword-spotter-microphone \
|
|
--tokens=/path/to/tokens.txt \
|
|
--encoder=/path/to/encoder.onnx \
|
|
--decoder=/path/to/decoder.onnx \
|
|
--joiner=/path/to/joiner.onnx \
|
|
--provider=cpu \
|
|
--num-threads=1 \
|
|
--keywords-file=keywords.txt
|
|
|
|
Please refer to
|
|
https://k2-fsa.github.io/sherpa/onnx/kws/pretrained_models/index.html
|
|
for a list of pre-trained models to download.
|
|
)usage";
|
|
|
|
sherpa_onnx::ParseOptions po(kUsageMessage);
|
|
sherpa_onnx::KeywordSpotterConfig config;
|
|
|
|
config.Register(&po);
|
|
po.Read(argc, argv);
|
|
if (po.NumArgs() != 0) {
|
|
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::KeywordSpotter spotter(config);
|
|
auto s = spotter.CreateStream();
|
|
|
|
sherpa_onnx::Microphone mic;
|
|
|
|
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-keyword-spotter-alsa \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);
|
|
}
|
|
|
|
mic.PrintDevices(device_index);
|
|
|
|
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);
|
|
}
|
|
|
|
if (!mic.OpenDevice(device_index, mic_sample_rate, 1, RecordCallback,
|
|
s.get())) {
|
|
fprintf(stderr, "portaudio error: %d\n", device_index);
|
|
exit(EXIT_FAILURE);
|
|
}
|
|
|
|
int32_t keyword_index = 0;
|
|
sherpa_onnx::Display display;
|
|
while (!stop) {
|
|
while (spotter.IsReady(s.get())) {
|
|
spotter.DecodeStream(s.get());
|
|
|
|
const auto r = spotter.GetResult(s.get());
|
|
if (!r.keyword.empty()) {
|
|
display.Print(keyword_index, r.AsJsonString());
|
|
fflush(stderr);
|
|
keyword_index++;
|
|
|
|
spotter.Reset(s.get());
|
|
}
|
|
}
|
|
|
|
Pa_Sleep(20); // sleep for 20ms
|
|
}
|
|
|
|
return 0;
|
|
}
|