Whisper-base

Introduction

Whisper is a pre-trained Automatic Speech Recognition (ASR) and speech translation model. Trained on 680,000 hours of labeled data, this model demonstrates strong generalization capabilities across multiple datasets and domains without the need for fine-tuning.

Available NPU Models

whisper-base

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

• This model supports multilingual speech recognition and translation.

• Encoding time: 660.31 ms

• Average decoding time: 51.11 ms

Installation

apt install llm-model-whisper-base

• Download llm-model-whisper-base

Supported Platforms: Raspberry Pi5

Installation

sudo apt install llm-model-whisper-base-axcl

• Download llm-model-whisper-base-axcl

Supported Platforms: AI Pyramid

Installation

apt install llm-model-whisper-base-ax650

• Download llm-model-whisper-base-ax650