README.md

metadata

license: mit
pipeline_tag: automatic-speech-recognition
base_model:
  - ggerganov/whisper.cpp

Whisper Models for Lopatnov.Translate

This repository contains Whisper models for the Lopatnov.Translate service. These files are mirrors of the original models from the ggerganov/whisper.cpp repository.

Configuration

To configure model for the service, please modify appsettings.json:

Example configuration:

{
  "Models": {
    "whisper-small": {
        "Type": "Whisper",
        "Path": "../../models/audio-to-text/whisper.cpp/ggml-small.bin"
    },
  
    // or
  
    "whisper-medium": {
      "Type": "Whisper",
      "Path": "../../models/audio-to-text/whisper.cpp/ggml-medium.bin"
    }
  },

  "Translation": {
    "AudioToText": "whisper-small"   // use the name of the model configuration above
  }
}

Note: Make sure the Path correctly points to the location of your downloaded .bin files relative to application.

Documentation

For advanced configuration options, visit the Official Documentation.