ovos-stt-plugin-whispercpp 0.0.2a1

A whispercpp stt plugin for OpenVoiceOS

Description

OpenVoiceOS STT plugin for whispercpp

High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model:

• Plain C/C++ implementation without dependencies
• Apple silicon first-class citizen - optimized via Arm Neon and Accelerate framework
• AVX intrinsics support for x86 architectures
• Mixed F16 / F32 precision
• Low memory usage (Flash Attention + Flash Forward)
• Zero memory allocations at runtime
• Runs on the CPU

Install

pip install ovos-stt-plugin-whispercpp

Configuration

available models are "tiny.en", "tiny", "base.en", "base", "small.en", "small", "medium.en", "medium", "large"

  "stt": {
    "module": "ovos-stt-plugin-whispercpp",
    "ovos-stt-plugin-whispercpp": {
        "model": "tiny"
    }
  }
 

Models

Models will be autodownloaded to ~/.local/share/pywhispercpp/models/{model_name} when plugin is loaded

Memory usage

Model	Disk	Mem
tiny	75 MB	~280 MB
base	142 MB	~430 MB
small	466 MB	~1.0 GB
medium	1.5 GB	~2.6 GB
large	2.9 GB	~4.7 GB