enginex-mr_series-sherpa-onnx/sherpa-onnx/csrc/sherpa-onnx-microphone.cc

// sherpa-onnx/csrc/sherpa-onnx-microphone.cc
//
// Copyright (c)  2022-2023  Xiaomi Corporation

#include <signal.h>
#include <stdio.h>
#include <stdlib.h>

#include <algorithm>
#include <cctype>  // std::tolower

#include "portaudio.h"  // NOLINT
#include "sherpa-onnx/csrc/display.h"
#include "sherpa-onnx/csrc/microphone.h"
#include "sherpa-onnx/csrc/online-recognizer.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 speech recognition.
Usage:

  ./bin/sherpa-onnx-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 \
    --decoding-method=greedy_search

Please refer to
https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html
for a list of pre-trained models to download.
)usage";

  sherpa_onnx::ParseOptions po(kUsageMessage);
  sherpa_onnx::OnlineRecognizerConfig 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::OnlineRecognizer recognizer(config);
  auto s = recognizer.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);
  }

  std::string last_text;
  int32_t segment_index = 0;
  sherpa_onnx::Display display;
  while (!stop) {
    while (recognizer.IsReady(s.get())) {
      recognizer.DecodeStream(s.get());
    }

    auto text = recognizer.GetResult(s.get()).text;
    bool is_endpoint = recognizer.IsEndpoint(s.get());

    if (!text.empty() && last_text != text) {
      last_text = text;

      std::transform(text.begin(), text.end(), text.begin(),
                     [](auto c) { return std::tolower(c); });

      fprintf(stderr, "\r%d: %s", segment_index, text.c_str());
      fflush(stderr);
    }

    if (is_endpoint) {
      if (!text.empty()) {
        ++segment_index;
        fprintf(stderr, "\n");
      }

      recognizer.Reset(s.get());
    }

    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;
}