← Back to models

Whisper tiny

transcriberAudio

Turn speech recordings into text with the smallest Whisper checkpoint, 39M parameters, for fast local transcription.

antfly inference pull openai/whisper-tiny
By openaiLicense: apache-2.0Hugging Face source

Technical Specs

Architecture
Whisper tiny
Parameters
39M
multilingual

Usage

Pull the model

antfly inference pull openai/whisper-tiny

Start Antfly Inference

# With Antfly standalone (Antfly Inference enabled by default)
antfly standalone

# Or run Antfly Inference on its own, listening on 127.0.0.1:8090
antfly inference run

Use in configuration

{
  "transcribers": {
    "local": {
      "provider": "antfly",
      "model": "openai/whisper-tiny"
    }
  }
}