mirror of
https://github.com/78/xiaozhi-esp32.git
synced 2026-02-19 18:38:09 +00:00
* add: Moji 2 has built-in ESP32-C5 dual band Wi-Fi * feat: PowerSaveTimer 160 >> 240 * fix(audio): add frame buffering to NoAudioProcessor On chips where CONFIG_USE_AUDIO_PROCESSOR is unavailable (e.g., ESP32-C5, which is excluded by Kconfig despite having PSRAM), NoAudioProcessor is used. The original implementation passed through 160-sample chunks directly, but the Opus encoder expects 960 samples (60ms @ 16kHz), resulting in frame size mismatch errors, high CPU usage, and watchdog resets. Added output_buffer_ to accumulate audio samples until reaching frame_samples_ (960) before outputting, matching AfeAudioProcessor behavior. other: Turn off sleep mode (PowerSaveTimer)
72 lines
2.0 KiB
C++
72 lines
2.0 KiB
C++
#include "no_audio_processor.h"
|
|
#include <esp_log.h>
|
|
|
|
#define TAG "NoAudioProcessor"
|
|
|
|
void NoAudioProcessor::Initialize(AudioCodec* codec, int frame_duration_ms, srmodel_list_t* models_list) {
|
|
codec_ = codec;
|
|
frame_samples_ = frame_duration_ms * 16000 / 1000;
|
|
output_buffer_.reserve(frame_samples_);
|
|
}
|
|
|
|
void NoAudioProcessor::Feed(std::vector<int16_t>&& data) {
|
|
if (!is_running_ || !output_callback_) {
|
|
return;
|
|
}
|
|
|
|
// Convert stereo to mono if needed
|
|
if (codec_->input_channels() == 2) {
|
|
for (size_t i = 0, j = 0; i < data.size() / 2; ++i, j += 2) {
|
|
output_buffer_.push_back(data[j]);
|
|
}
|
|
} else {
|
|
output_buffer_.insert(output_buffer_.end(), data.begin(), data.end());
|
|
}
|
|
|
|
// Output complete frames when buffer has enough data
|
|
while (output_buffer_.size() >= (size_t)frame_samples_) {
|
|
if (output_buffer_.size() == (size_t)frame_samples_) {
|
|
output_callback_(std::move(output_buffer_));
|
|
output_buffer_.clear();
|
|
output_buffer_.reserve(frame_samples_);
|
|
} else {
|
|
output_callback_(std::vector<int16_t>(output_buffer_.begin(), output_buffer_.begin() + frame_samples_));
|
|
output_buffer_.erase(output_buffer_.begin(), output_buffer_.begin() + frame_samples_);
|
|
}
|
|
}
|
|
}
|
|
|
|
void NoAudioProcessor::Start() {
|
|
is_running_ = true;
|
|
}
|
|
|
|
void NoAudioProcessor::Stop() {
|
|
is_running_ = false;
|
|
output_buffer_.clear();
|
|
}
|
|
|
|
bool NoAudioProcessor::IsRunning() {
|
|
return is_running_;
|
|
}
|
|
|
|
void NoAudioProcessor::OnOutput(std::function<void(std::vector<int16_t>&& data)> callback) {
|
|
output_callback_ = callback;
|
|
}
|
|
|
|
void NoAudioProcessor::OnVadStateChange(std::function<void(bool speaking)> callback) {
|
|
vad_state_change_callback_ = callback;
|
|
}
|
|
|
|
size_t NoAudioProcessor::GetFeedSize() {
|
|
if (!codec_) {
|
|
return 0;
|
|
}
|
|
return frame_samples_;
|
|
}
|
|
|
|
void NoAudioProcessor::EnableDeviceAec(bool enable) {
|
|
if (enable) {
|
|
ESP_LOGE(TAG, "Device AEC is not supported");
|
|
}
|
|
}
|