This repository has been archived on 2025-08-26. You can view files and clone it, but cannot push or open issues or pull requests.
Files
enginex_bi_series-sherpa-onnx/sherpa-onnx/csrc/sherpa-onnx-keyword-spotter-microphone.cc
Wei Kang 734bbd91dc Add Python API for keyword spotting (#576)
* Add alsa & microphone support for keyword spotting

* Add python wrapper
2024-03-01 09:31:11 +08:00

149 lines
4.1 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/microphone.h"
#include "sherpa-onnx/csrc/keyword-spotter.h"
bool stop = false;
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(16000, 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;
PaDeviceIndex num_devices = Pa_GetDeviceCount();
fprintf(stderr, "Num devices: %d\n", num_devices);
PaStreamParameters param;
param.device = Pa_GetDefaultInputDevice();
if (param.device == paNoDevice) {
fprintf(stderr, "No default input device found\n");
exit(EXIT_FAILURE);
}
fprintf(stderr, "Use default 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 sample_rate = 16000;
PaStream *stream;
PaError err =
Pa_OpenStream(&stream, &param, nullptr, /* &outputParameters, */
sample_rate,
0, // frames per buffer
paClipOff, // we won't output out of range samples
// so don't bother clipping them
RecordCallback, s.get());
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);
}
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++;
}
Pa_Sleep(20); // sleep for 20ms
}
err = Pa_CloseStream(stream);
if (err != paNoError) {
fprintf(stderr, "portaudio error: %s\n", Pa_GetErrorText(err));
exit(EXIT_FAILURE);
}
return 0;
}