Keyword Spotting

Introduction

Keyword Spotting (KWS) models are designed to detect specific keywords in audio streams. These models are useful in applications such as voice assistants, smart home devices, and other scenarios where recognizing specific commands or phrases is essential.

Available CPU Models

llm-model-sherpa-onnx-kws-zipformer-gigaspeech-3.3m-2024-01-01

Support Platforms: LLM630 Compute Kit, Module LLM, and Module LLM Kit

• This model is trained on the GigaSpeech dataset and supports keyword spotting tasks.

• This model only supports English.

Install

apt install llm-model-sherpa-onnx-kws-zipformer-gigaspeech-3.3m-2024-01-01

• Download llm-model-sherpa-onnx-kws-zipformer-gigaspeech-3.3m-2024-01-01

llm-model-sherpa-onnx-kws-zipformer-wenetspeech-3.3m-2024-01-01

Support Platforms: LLM630 Compute Kit, Module LLM, and Module LLM Kit

• This model is trained on the WenetSpeech dataset and supports keyword spotting tasks.

• This model only supports Chinese.

Install

apt install llm-model-sherpa-onnx-kws-zipformer-wenetspeech-3.3m-2024-01-01

• Download llm-model-sherpa-onnx-kws-zipformer-wenetspeech-3.3m-2024-01-01