StackFlow AI Platform
Devices & Quick Start
Models
Qwen3
DeepSeek-R1
AI Pyramid Applications
Module LLM Applications
CV Vision Application
Vision Language Model (VLM)
Large Language Model (LLM)
Voice Assistant
Automatic Speech Recognition (ASR)
Introduction
Automatic Speech Recognition (ASR) models are designed to convert spoken language into text. These models are widely used in scenarios such as transcription services, voice-controlled systems, and assistive tools.
Available CPU Models
llm-model-sherpa-ncnn-streaming-zipformer-20m-2023-02-17
Supported Platforms: LLM630 Compute Kit, Module LLM, Module LLM Kit, and AI Pyramid
This model is a streaming ASR model based on the Zipformer architecture. It is trained on large-scale datasets and provides high-accuracy speech recognition performance.
This model supports English only.
Installation
apt install llm-model-sherpa-ncnn-streaming-zipformer-20m-2023-02-17llm-model-sherpa-ncnn-streaming-zipformer-zh-14m-2023-02-23
Supported Platforms: LLM630 Compute Kit, Module LLM, Module LLM Kit, and AI Pyramid
This model is a streaming ASR model based on the Zipformer architecture. It is trained on large-scale datasets and provides high-accuracy speech recognition performance.
This model supports Chinese only.
Installation
apt install llm-model-sherpa-ncnn-streaming-zipformer-zh-14m-2023-02-23