最終更新:2025-01-20 (月) 12:20:53 (597d)
M5ModuleLLM/サンプル
Top / M5ModuleLLM / サンプル
Arduino IDE
サンプル 機能 M5ModuleLLM/サンプル/KWS_ASR AUDIO:
KWS
en: sherpa-onnx-kws-zipformer-gigaspeech-3.3M-2024-01-01
zh: sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
ASR:
en: sherpa-ncnn-streaming-zipformer-20M-2023-02-17
zh: sherpa-ncnn-streaming-zipformer-zh-14M-2023-02-23M5ModuleLLM/サンプル/TTS AUDIO
TTS: SummerTTS
en: single_speaker_english_fast?
zh: single_speaker_fast?M5ModuleLLM/サンプル/TextAssistant LLM: Qwen2.5-0.5B-Instruct M5ModuleLLM/サンプル/SerialTextAssistant LLM: Qwen2.5-0.5B-Instruct M5ModuleLLM/サンプル/VoiceAssistant KWS
en: sherpa-onnx-kws-zipformer-gigaspeech-3.3M-2024-01-01
zh: sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
ASR
en: sherpa-ncnn-streaming-zipformer-20M-2023-02-17
zh: sherpa-ncnn-streaming-zipformer-zh-14M-2023-02-23
LLM: Qwen2.5-0.5B-Instruct
TTS: MeloTTS
en/zh: melotts_zh-cn
(SummerTTS as fallback)
en: single_speaker_english_fast?
zh: single_speaker_fast?M5ModuleLLM/サンプル/YOLO? CAMERA: /dev/video0
YOLO: yolo11n
メモ
- kws_asr: Uses KWS to wake up and triggers ASR for speech-to-text conversion. (KWS+ASR)
- text_assistant: Inputs text into the LLM model, performs inference, and outputs the result in text form. (LLM)
- tts: Uses the TTS unit to convert text to speech for playback. (TTS)
- voice_assistant: Uses KWS to wake up, triggers ASR for speech-to-text conversion, inputs the converted text into the LLM for inference, and outputs the inference result through TTS as speech. (KWS+ASR+LLM+TTS)
