whisper-tiny-genai

Overview

openai/whisper-tiny exported to ONNX Runtime GenAI format with separate encoder and decoder ONNX files plus external data files.

Model Details

• Source model: openai/whisper-tiny
• Format: ONNX Runtime GenAI encoder/decoder split
• Runtime target: ONNX Runtime GenAI
• Precision: not documented in this repository

Files

File	Description
encoder.onnx + encoder.onnx.data	Encoder model
decoder.onnx + decoder.onnx.data	Decoder model
genai_config.json	ONNX Runtime GenAI session configuration
audio_processor_config.json	Audio feature extraction configuration
tokenizer.json + tokenizer_config.json	Tokenizer files

Intended Use

Run the converted Whisper tiny automatic speech recognition model with ONNX Runtime GenAI.

Training Data

This repository does not document training data. See the upstream source model for training data information.

Evaluation

This repository does not report conversion-specific evaluation results.

Limitations

• Conversion validation results are not documented in this repository.
• Performance and accuracy may differ from the upstream model depending on runtime, execution provider, and decoding configuration.
• Training data and evaluation details are inherited from the upstream model documentation, not reproduced here.

License

Apache-2.0, matching the upstream openai/whisper-tiny model.