StackFlow AI Platform
Devices & Quick Start
LLM630 Compute Kit
Models
Qwen3
DeepSeek-R1
Applications
CV Vision Application
Vision Language Model (VLM)
Large Language Model (LLM)
Voice Assistant
Module LLM - Speech-to-Text
This example demonstrates how to use the M5ModuleLLM library to perform Keyword Spotting (KWS), Voice Activity Detection (VAD), and Automatic Speech Recognition (ASR) using the Whisper model.
Preparation
Refer to the Module LLM Arduino Quick Start to complete basic environment setup and install the M5ModuleLLM driver library.
Refer to the Module LLM Software Package Update Guide to install the following model and software packages:
apt install llm-whisper llm-kws llm-vadapt install llm-model-whisper-tiny llm-model-silero-vad llm-model-sherpa-onnx-kws-zipformer-gigaspeech-3.3m-2024-01-01- The following example uses the hardware:
STT CoreS3
/*
* SPDX-FileCopyrightText: 2024 M5Stack Technology CO LTD
*
* SPDX-License-Identifier: MIT
*/
#include <Arduino.h>
#include <M5Unified.h>
#include <M5ModuleLLM.h>
M5ModuleLLM module_llm;
/* Must be capitalized */
String wake_up_keyword = "HELLO";
String kws_work_id;
String vad_work_id;
String whisper_work_id;
String language;
void setup()
{
M5.begin();
M5.Display.setTextSize(2);
M5.Display.setTextScroll(true);
language = "en_US";
/* Init module serial port */
int rxd = M5.getPin(m5::pin_name_t::port_c_rxd);
int txd = M5.getPin(m5::pin_name_t::port_c_txd);
Serial2.begin(115200, SERIAL_8N1, rxd, txd);
/* Init module */
module_llm.begin(&Serial2);
/* Make sure module is connected */
M5.Display.printf(">> Check ModuleLLM connection..\n");
while (1) {
if (module_llm.checkConnection()) {
break;
}
}
/* Reset ModuleLLM */
M5.Display.printf(">> Reset ModuleLLM..\n");
module_llm.sys.reset();
/* Setup Audio module */
M5.Display.printf(">> Setup audio..\n");
module_llm.audio.setup();
/* Setup KWS module and save returned work id */
M5.Display.printf(">> Setup kws..\n");
m5_module_llm::ApiKwsSetupConfig_t kws_config;
kws_config.kws = wake_up_keyword;
kws_work_id = module_llm.kws.setup(kws_config, "kws_setup", language);
/* Setup VAD module and save returned work id */
M5.Display.printf(">> Setup vad..\n");
m5_module_llm::ApiVadSetupConfig_t vad_config;
vad_config.input = {"sys.pcm", kws_work_id};
vad_work_id = module_llm.vad.setup(vad_config, "vad_setup");
/* Setup Whisper module and save returned work id */
M5.Display.printf(">> Setup whisper..\n");
m5_module_llm::ApiWhisperSetupConfig_t whisper_config;
whisper_config.input = {"sys.pcm", kws_work_id, vad_work_id};
whisper_config.language = "en";
whisper_work_id = module_llm.whisper.setup(whisper_config, "whisper_setup");
M5.Display.printf(">> Setup ok\n>> Say \"%s\" to wakeup\n", wake_up_keyword.c_str());
}
void loop()
{
/* Update ModuleLLM */
module_llm.update();
/* Handle module response messages */
for (auto& msg : module_llm.msg.responseMsgList) {
/* If KWS module message */
if (msg.work_id == kws_work_id) {
M5.Display.setTextColor(TFT_GREENYELLOW);
M5.Display.printf(">> Keyword detected\n");
}
/* If ASR module message */
if (msg.work_id == whisper_work_id) {
/* Check message object type */
if (msg.object == "asr.utf-8") {
/* Parse message json and get ASR result */
JsonDocument doc;
deserializeJson(doc, msg.raw_msg);
String asr_result = doc["data"].as<String>();
M5.Display.setTextColor(TFT_YELLOW);
M5.Display.printf(">> %s\n", asr_result.c_str());
}
}
}
/* Clear handled messages */
module_llm.msg.responseMsgList.clear();
}- Upload the code to CoreS3.
- After initialization, use the wake word hello to wake up the module. When successful, “Keyword detected” will be shown. After that, continue speaking, and after a short pause, the audio will be automatically transcribed and the ASR result will be displayed.
