ModelVerifiedExternal

Whisper Small Genai

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

Sourcehuggingface.co/tonythethompson/Whisper-Small-GenAI-ONNX/tree/c89e1ceda14dbd574887c0585fc46437824fcff1

KindOtherBase modelopenai/whisper-smallVersionRevision c89e1cePublisher@tonythethompsonCgrade

Model source

Kind: Other
File size: 94.5–134 KB
Base model: openai/whisper-small
Version: vRevision c89e1ce
Updated: Oct 3, 2026
Publisher: @tonythethompson
Downloads: 0
Source: Hugging Face

Source description

whisper-small-genai

Overview

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

Source

Field	Value
Upstream model	openai/whisper-small
Upstream source revision	`973afd24965f72e36ca33b3055d56a652f456b4d`
Export tool/script	ONNX Runtime GenAI model builder (`onnxruntime-genai`)
Quantization recipe	FP32 weights in GenAI encoder/decoder ONNX layout

Precision and Packaging

Export tooling, precision, and quantization are recorded in the Source table above. This packaging mirror does not publish independent parity benchmarks; validate on your target execution provider before production use.

Model Details

Source model: openai/whisper-small
Parameters: 244M
Format: ONNX Runtime GenAI encoder/decoder split
Runtime target: ONNX Runtime GenAI

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 small 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

Limitations

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-small model.

Sources

1 source

Hugging FacePrimaryVersion c89e1ceda14dbd574887c0585fc46437824fcff1

huggingface.co/tonythethompson/Whisper-Small-GenAI-ONNX/tree/c89e1ceda14dbd574887c0585fc46437824fcff1

Verified Oct 3

Download files

Model artifacts

2 artifacts

decoder.onnx

onnx · 134 KB · SHA-256 ddc6119992fa…b1e7 · Hugging Face

Download file

encoder.onnx

onnx · 94.5 KB · SHA-256 3a3d4093374a…66a7 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeJul 11huggingface.co/tonythethompson/Whisper-Small-GenAI-ONNX

--- license: apache-2.0 base_model: openai/whisper-small pipeline_tag: automatic-speech-recognition library_name: onnxruntime-genai language: - multilingual tags: - onnx - onnxruntime-genai - whisper - automatic-speech-recognition --- # whisper-small-genai ## Overview `openai/whisper-small` exported to ONNX Runtime GenAI format with separate encoder and decoder ONNX files plus external data files. ## Source | Field | Value | |---|---| | Upstream model | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | | Upstream source revision | `973afd24965f72e36ca33b3055d56a652f456b4d` | | Export tool/script | ONNX Runtime GenAI model builder (`onnxruntime-genai`) | | Quantization recipe | FP32 weights in GenAI encoder/decoder ONNX layout | ## Precision and Packaging Export tooling, precision, and quantization are recorded in the **Source** table above. This packaging mirror does not publish independent parity benchmarks; validate on your target execution provider before production use. ## Model Details - Source model: [`openai/whisper-small`](https://huggingface.co/openai/whisper-small) - Parameters: 244M - Format: ONNX Runtime GenAI encoder/decoder split - Runtime target: ONNX Runtime GenAI ## 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 small 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 ## Limitations - 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-small`](https://huggingface.co/openai/whisper-small) model.

NoteJul 11huggingface.co/tonythethompson/Whisper-Small-GenAI-ONNX

Source context: 0 downloads · 1 likes · Pipeline automatic-speech-recognition · Library onnxruntime-genai · Repo tonythethompson/Whisper-Small-GenAI-ONNX

NoteMay 19huggingface.co/api/models/tonythethompson/whisper-small-genai

Source context: 0 downloads · 0 likes · Repo tonythethompson/whisper-small-genai