Skip to content

Lightblues/ncnn_mcp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ncnn-mcp

NCNN Whisper Audio Transcription MCP Server

Prepare model

  • download whisper model as iwiki;
  • prepare the input audio file, e.g. from openai.

reference data structure:

.
├── data
│   └── alloy.wav
├── model
│   ├── data
│   └── whisper
│       ├── whisper
│       ├── whisper_tiny_decoder.ncnn.bin
│       ├── ...
│       └── whisper_vocab.txt

Run

  1. Option 1: insall as a mcp server, ref config file mcp_config.json
    1. You can test MCP tools with the official tool Inspector.
  2. Option 2: test locally.
# install dependencies
uv sync
# test whisper binary
uv run python test/run_whisper.py
# test mcp server
uv run python test/test_server.py

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages