README.md

metadata

license: mit
language:
  - en
  - de
  - fr
  - es
  - pt
  - it
base_model:
  - openai/whisper-small
pipeline_tag: automatic-speech-recognition

Whisper ONNX Optimized Models

Optimized Whisper ONNX models packaged for easy deployment. Each zip contains all necessary files for inference.

Models Available

Model	Language	Size	Target Use	Download
Small English	English-only	107MB	Fast English transcription	whisper-small-en-onnx.zip
Small Multilingual	99 languages	245MB	Fast multilingual transcription	whisper-small-multilingual-onnx.zip
Medium English	English-only	247MB	High quality English transcription	whisper-medium-en-onnx.zip
Medium Multilingual	99 languages	602MB	High quality multilingual	whisper-medium-multilingual-onnx.zip
Large v3 Turbo	99 languages	646MB	Best quality, fastest large model	whisper-large-v3-turbo-onnx.zip

Contents of Each Zip

Each zip file contains 6 files needed for inference:

ONNX Model Files

• encoder_model_quantized.onnx - Audio encoder (processes mel spectrograms)
• decoder_with_past_model_quantized.onnx - Text decoder (generates transcription), optimized decoder with KV caching

Configuration Files

• config.json - Model configuration
• generation_config.json - Generation parameters
• preprocessor_config.json - Audio preprocessing settings
• tokenizer.json - Tokenizer vocabulary

Model Sources

These models are repackaged from:

• Distil-Whisper (English models)
• ONNX Community (Multilingual models)

License

Models inherit their original licenses:

• Distil-Whisper models: MIT License
• Whisper models: MIT License

Version History

• v1.0.0 - Initial release with 5 optimized models