forked from xiaozhi/xiaozhi-esp32
* Adapt boards to v2 partition tables * fix esp log error * fix display style * reset emotion after download assets * fix compiling * update assets default url * Add user only tools * Add image cache * smaller cache and buffer, more heap * use MAIN_EVENT_CLOCK_TICK to avoid audio glitches * bump to 2.0.0 * fix compiling errors --------- Co-authored-by: Xiaoxia <terrence.huang@tenclass.com>
191 lines
6.5 KiB
C++
191 lines
6.5 KiB
C++
#include "custom_wake_word.h"
|
|
#include "audio_service.h"
|
|
#include "system_info.h"
|
|
|
|
#include <esp_log.h>
|
|
#include "esp_mn_iface.h"
|
|
#include "esp_mn_models.h"
|
|
#include "esp_mn_speech_commands.h"
|
|
|
|
|
|
#define TAG "CustomWakeWord"
|
|
|
|
|
|
CustomWakeWord::CustomWakeWord()
|
|
: wake_word_pcm_(), wake_word_opus_() {
|
|
}
|
|
|
|
CustomWakeWord::~CustomWakeWord() {
|
|
if (multinet_model_data_ != nullptr && multinet_ != nullptr) {
|
|
multinet_->destroy(multinet_model_data_);
|
|
multinet_model_data_ = nullptr;
|
|
}
|
|
|
|
if (wake_word_encode_task_stack_ != nullptr) {
|
|
heap_caps_free(wake_word_encode_task_stack_);
|
|
}
|
|
|
|
if (wake_word_encode_task_buffer_ != nullptr) {
|
|
heap_caps_free(wake_word_encode_task_buffer_);
|
|
}
|
|
|
|
if (models_ != nullptr) {
|
|
esp_srmodel_deinit(models_);
|
|
}
|
|
}
|
|
|
|
bool CustomWakeWord::Initialize(AudioCodec* codec, srmodel_list_t* models_list) {
|
|
codec_ = codec;
|
|
|
|
if (models_list == nullptr) {
|
|
models_ = esp_srmodel_init("model");
|
|
} else {
|
|
models_ = models_list;
|
|
}
|
|
|
|
if (models_ == nullptr || models_->num == -1) {
|
|
ESP_LOGE(TAG, "Failed to initialize wakenet model");
|
|
return false;
|
|
}
|
|
|
|
// 初始化 multinet (命令词识别)
|
|
mn_name_ = esp_srmodel_filter(models_, ESP_MN_PREFIX, ESP_MN_CHINESE);
|
|
if (mn_name_ == nullptr) {
|
|
ESP_LOGE(TAG, "Failed to initialize multinet, mn_name is nullptr");
|
|
ESP_LOGI(TAG, "Please refer to https://pcn7cs20v8cr.feishu.cn/wiki/CpQjwQsCJiQSWSkYEvrcxcbVnwh to add custom wake word");
|
|
return false;
|
|
}
|
|
|
|
ESP_LOGI(TAG, "multinet: %s", mn_name_);
|
|
multinet_ = esp_mn_handle_from_name(mn_name_);
|
|
multinet_model_data_ = multinet_->create(mn_name_, 3000); // 3 秒超时
|
|
multinet_->set_det_threshold(multinet_model_data_, CONFIG_CUSTOM_WAKE_WORD_THRESHOLD / 100.0f);
|
|
esp_mn_commands_clear();
|
|
esp_mn_commands_add(1, CONFIG_CUSTOM_WAKE_WORD);
|
|
esp_mn_commands_update();
|
|
|
|
multinet_->print_active_speech_commands(multinet_model_data_);
|
|
return true;
|
|
}
|
|
|
|
void CustomWakeWord::OnWakeWordDetected(std::function<void(const std::string& wake_word)> callback) {
|
|
wake_word_detected_callback_ = callback;
|
|
}
|
|
|
|
void CustomWakeWord::Start() {
|
|
running_ = true;
|
|
}
|
|
|
|
void CustomWakeWord::Stop() {
|
|
running_ = false;
|
|
}
|
|
|
|
void CustomWakeWord::Feed(const std::vector<int16_t>& data) {
|
|
if (multinet_model_data_ == nullptr || !running_) {
|
|
return;
|
|
}
|
|
|
|
esp_mn_state_t mn_state;
|
|
// If input channels is 2, we need to fetch the left channel data
|
|
if (codec_->input_channels() == 2) {
|
|
auto mono_data = std::vector<int16_t>(data.size() / 2);
|
|
for (size_t i = 0, j = 0; i < mono_data.size(); ++i, j += 2) {
|
|
mono_data[i] = data[j];
|
|
}
|
|
|
|
StoreWakeWordData(mono_data);
|
|
mn_state = multinet_->detect(multinet_model_data_, const_cast<int16_t*>(mono_data.data()));
|
|
} else {
|
|
StoreWakeWordData(data);
|
|
mn_state = multinet_->detect(multinet_model_data_, const_cast<int16_t*>(data.data()));
|
|
}
|
|
|
|
if (mn_state == ESP_MN_STATE_DETECTING) {
|
|
return;
|
|
} else if (mn_state == ESP_MN_STATE_DETECTED) {
|
|
esp_mn_results_t *mn_result = multinet_->get_results(multinet_model_data_);
|
|
ESP_LOGI(TAG, "Custom wake word detected: command_id=%d, string=%s, prob=%f",
|
|
mn_result->command_id[0], mn_result->string, mn_result->prob[0]);
|
|
|
|
if (mn_result->command_id[0] == 1) {
|
|
last_detected_wake_word_ = CONFIG_CUSTOM_WAKE_WORD_DISPLAY;
|
|
}
|
|
running_ = false;
|
|
|
|
if (wake_word_detected_callback_) {
|
|
wake_word_detected_callback_(last_detected_wake_word_);
|
|
}
|
|
multinet_->clean(multinet_model_data_);
|
|
} else if (mn_state == ESP_MN_STATE_TIMEOUT) {
|
|
ESP_LOGD(TAG, "Command word detection timeout, cleaning state");
|
|
multinet_->clean(multinet_model_data_);
|
|
}
|
|
}
|
|
|
|
size_t CustomWakeWord::GetFeedSize() {
|
|
if (multinet_model_data_ == nullptr) {
|
|
return 0;
|
|
}
|
|
return multinet_->get_samp_chunksize(multinet_model_data_);
|
|
}
|
|
|
|
void CustomWakeWord::StoreWakeWordData(const std::vector<int16_t>& data) {
|
|
// store audio data to wake_word_pcm_
|
|
wake_word_pcm_.push_back(data);
|
|
// keep about 2 seconds of data, detect duration is 30ms (sample_rate == 16000, chunksize == 512)
|
|
while (wake_word_pcm_.size() > 2000 / 30) {
|
|
wake_word_pcm_.pop_front();
|
|
}
|
|
}
|
|
|
|
void CustomWakeWord::EncodeWakeWordData() {
|
|
const size_t stack_size = 4096 * 7;
|
|
wake_word_opus_.clear();
|
|
if (wake_word_encode_task_stack_ == nullptr) {
|
|
wake_word_encode_task_stack_ = (StackType_t*)heap_caps_malloc(stack_size, MALLOC_CAP_SPIRAM);
|
|
assert(wake_word_encode_task_stack_ != nullptr);
|
|
}
|
|
if (wake_word_encode_task_buffer_ == nullptr) {
|
|
wake_word_encode_task_buffer_ = (StaticTask_t*)heap_caps_malloc(sizeof(StaticTask_t), MALLOC_CAP_INTERNAL);
|
|
assert(wake_word_encode_task_buffer_ != nullptr);
|
|
}
|
|
|
|
wake_word_encode_task_ = xTaskCreateStatic([](void* arg) {
|
|
auto this_ = (CustomWakeWord*)arg;
|
|
{
|
|
auto start_time = esp_timer_get_time();
|
|
auto encoder = std::make_unique<OpusEncoderWrapper>(16000, 1, OPUS_FRAME_DURATION_MS);
|
|
encoder->SetComplexity(0); // 0 is the fastest
|
|
|
|
int packets = 0;
|
|
for (auto& pcm: this_->wake_word_pcm_) {
|
|
encoder->Encode(std::move(pcm), [this_](std::vector<uint8_t>&& opus) {
|
|
std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
|
|
this_->wake_word_opus_.emplace_back(std::move(opus));
|
|
this_->wake_word_cv_.notify_all();
|
|
});
|
|
packets++;
|
|
}
|
|
this_->wake_word_pcm_.clear();
|
|
|
|
auto end_time = esp_timer_get_time();
|
|
ESP_LOGI(TAG, "Encode wake word opus %d packets in %ld ms", packets, (long)((end_time - start_time) / 1000));
|
|
|
|
std::lock_guard<std::mutex> lock(this_->wake_word_mutex_);
|
|
this_->wake_word_opus_.push_back(std::vector<uint8_t>());
|
|
this_->wake_word_cv_.notify_all();
|
|
}
|
|
vTaskDelete(NULL);
|
|
}, "encode_wake_word", stack_size, this, 2, wake_word_encode_task_stack_, wake_word_encode_task_buffer_);
|
|
}
|
|
|
|
bool CustomWakeWord::GetWakeWordOpus(std::vector<uint8_t>& opus) {
|
|
std::unique_lock<std::mutex> lock(wake_word_mutex_);
|
|
wake_word_cv_.wait(lock, [this]() {
|
|
return !wake_word_opus_.empty();
|
|
});
|
|
opus.swap(wake_word_opus_.front());
|
|
wake_word_opus_.pop_front();
|
|
return !opus.empty();
|
|
}
|