zukky/LiteASR-ONNX-DLL

By zukky · ↓ 0 · ♥ 0 · Updated 2026-02-03

What's in this repo

This page lists the files in zukky/LiteASR-ONNX-DLL, including decoder_model.onnx, decoder_with_past_model.onnx, encoder_model.onnx and more.

18 ONNX models (.onnx files)
81 files, including 48 .json, 18 .onnx, 6 .data, 3 .py, 2 .md, 1 .dll
Last updated 2026-02-03

ONNX files

File	Size	Download
models/efficient-speech__lite-whisper-large-v3-acc/onnx/decoder_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-acc/onnx/decoder_with_past_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-acc/onnx/encoder_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-fast/onnx/decoder_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-fast/onnx/decoder_with_past_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-fast/onnx/encoder_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-turbo-acc/onnx/decoder_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-turbo-acc/onnx/decoder_with_past_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-turbo-acc/onnx/encoder_model.onnx	—	Download
models/efficient-speech__lite-whisper-large-v3-turbo-fast/onnx/decoder_model.onnx	—	Download

Showing 10 of 18 .onnx files — see the full file list on the right.

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

--- license: apache-2.0 library_name: onnxruntime pipeline_tag: automatic-speech-recognition tags:

automatic-speech-recognition
whisper
onnx

LiteASR-ONNX release_dll bundle

This folder is generated by make_release_dll.ps1 and is prepared for distribution/use in Hugging Face style repositories.

It bundles:

Rust FFI DLL (bin/liteasr_ffi.dll)
C ABI header (include/liteasr_ffi.h)
Python FFI + ONNXRuntime client (ffi_python/)
ONNX/tokenizer assets (models/)
third-party dependency notes (thirdparty_licence.md)

Included models

(none copied)

Folder layout

bin/liteasr_ffi.dll: Rust FFI runtime library
include/liteasr_ffi.h: C ABI header for native bindings
ffi_python/liteasr_ffi.py: ctypes wrapper for DLL
ffi_python/onnx_transcribe_ffi.py: ONNXRuntime pipeline using DLL helpers
models/<model_name>/onnx/: ONNX files (encoder/decoder/decoder_with_past)
models/<model_name>/tokenizer/: tokenizer/config JSON files
thirdparty_licence.md: dependency license inventory

Quick start (Python)

cd ffi_python
uv run python onnx_transcribe_ffi.py --dll-path ..\bin\liteasr_ffi.dll --model-name efficient-speech__lite-whisper-large-v3-turbo-acc --audio ..\..\samples\a01.wav --out-dir ..\artifacts_a01

Regenerate bundle

All models:

./make_release_dll.ps1 -Clean -IncludeAllModels

Selected models:

./make_release_dll.ps1 -Clean -ModelNames efficient-speech__lite-whisper-large-v3-turbo-acc

Notes

Some ONNX exports may require .onnx.data sidecar files; these are copied when present.
Model weights/tokenizer terms are governed by the original model publishers.
thirdparty_licence.md is for engineering reference, not legal advice.

Model info

automatic-speech-recognition onnxruntime

onnxruntime onnx automatic-speech-recognition whisper license:apache-2.0 region:us

↓ 0 ♥ 0

Created: 2026-02-02

Updated: 2026-02-03

View on Hugging Face

Files (81)

.gitattributes

README.md

bin/liteasr_ffi.dll

ffi_python/__init__.py

ffi_python/liteasr_ffi.py

ffi_python/onnx_transcribe_ffi.py

ffi_python/requirements.txt

include/liteasr_ffi.h

models/efficient-speech__lite-whisper-large-v3-acc/onnx/decoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-acc/onnx/decoder_model.onnx.data

models/efficient-speech__lite-whisper-large-v3-acc/onnx/decoder_with_past_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-acc/onnx/decoder_with_past_model.onnx.data

models/efficient-speech__lite-whisper-large-v3-acc/onnx/encoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-acc/onnx/export_meta.json

models/efficient-speech__lite-whisper-large-v3-acc/tokenizer/config.json

models/efficient-speech__lite-whisper-large-v3-acc/tokenizer/generation_config.json

models/efficient-speech__lite-whisper-large-v3-acc/tokenizer/normalizer.json

models/efficient-speech__lite-whisper-large-v3-acc/tokenizer/preprocessor_config.json

models/efficient-speech__lite-whisper-large-v3-acc/tokenizer/special_tokens_map.json

models/efficient-speech__lite-whisper-large-v3-acc/tokenizer/tokenizer.json

models/efficient-speech__lite-whisper-large-v3-acc/tokenizer/tokenizer_config.json

models/efficient-speech__lite-whisper-large-v3-fast/onnx/decoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-fast/onnx/decoder_model.onnx.data

models/efficient-speech__lite-whisper-large-v3-fast/onnx/decoder_with_past_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-fast/onnx/decoder_with_past_model.onnx.data

models/efficient-speech__lite-whisper-large-v3-fast/onnx/encoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-fast/onnx/export_meta.json

models/efficient-speech__lite-whisper-large-v3-fast/tokenizer/config.json

models/efficient-speech__lite-whisper-large-v3-fast/tokenizer/generation_config.json

models/efficient-speech__lite-whisper-large-v3-fast/tokenizer/normalizer.json

models/efficient-speech__lite-whisper-large-v3-fast/tokenizer/preprocessor_config.json

models/efficient-speech__lite-whisper-large-v3-fast/tokenizer/special_tokens_map.json

models/efficient-speech__lite-whisper-large-v3-fast/tokenizer/tokenizer.json

models/efficient-speech__lite-whisper-large-v3-fast/tokenizer/tokenizer_config.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/onnx/decoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo-acc/onnx/decoder_with_past_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo-acc/onnx/encoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo-acc/onnx/export_meta.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/tokenizer/config.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/tokenizer/generation_config.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/tokenizer/normalizer.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/tokenizer/preprocessor_config.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/tokenizer/special_tokens_map.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/tokenizer/tokenizer.json

models/efficient-speech__lite-whisper-large-v3-turbo-acc/tokenizer/tokenizer_config.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/onnx/decoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo-fast/onnx/decoder_with_past_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo-fast/onnx/encoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo-fast/onnx/export_meta.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/tokenizer/config.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/tokenizer/generation_config.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/tokenizer/normalizer.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/tokenizer/preprocessor_config.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/tokenizer/special_tokens_map.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/tokenizer/tokenizer.json

models/efficient-speech__lite-whisper-large-v3-turbo-fast/tokenizer/tokenizer_config.json

models/efficient-speech__lite-whisper-large-v3-turbo/onnx/decoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo/onnx/decoder_with_past_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo/onnx/encoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3-turbo/onnx/export_meta.json

models/efficient-speech__lite-whisper-large-v3-turbo/tokenizer/config.json

models/efficient-speech__lite-whisper-large-v3-turbo/tokenizer/generation_config.json

models/efficient-speech__lite-whisper-large-v3-turbo/tokenizer/normalizer.json

models/efficient-speech__lite-whisper-large-v3-turbo/tokenizer/preprocessor_config.json

models/efficient-speech__lite-whisper-large-v3-turbo/tokenizer/special_tokens_map.json

models/efficient-speech__lite-whisper-large-v3-turbo/tokenizer/tokenizer.json

models/efficient-speech__lite-whisper-large-v3-turbo/tokenizer/tokenizer_config.json

models/efficient-speech__lite-whisper-large-v3/onnx/decoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3/onnx/decoder_model.onnx.data

models/efficient-speech__lite-whisper-large-v3/onnx/decoder_with_past_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3/onnx/decoder_with_past_model.onnx.data

models/efficient-speech__lite-whisper-large-v3/onnx/encoder_model.onnx ONNX

models/efficient-speech__lite-whisper-large-v3/onnx/export_meta.json

models/efficient-speech__lite-whisper-large-v3/tokenizer/config.json

models/efficient-speech__lite-whisper-large-v3/tokenizer/generation_config.json

models/efficient-speech__lite-whisper-large-v3/tokenizer/normalizer.json

models/efficient-speech__lite-whisper-large-v3/tokenizer/preprocessor_config.json

models/efficient-speech__lite-whisper-large-v3/tokenizer/special_tokens_map.json

models/efficient-speech__lite-whisper-large-v3/tokenizer/tokenizer.json

models/efficient-speech__lite-whisper-large-v3/tokenizer/tokenizer_config.json

thirdparty_licence.md

Related models

More automatic-speech-recognition models

Browse all automatic-speech-recognition models