onnxruntime/onnxruntime
petermcaughan f30e2d4387
Whisper Export (#15247)
### Description
Add scripts to export Whisper model to ONNX and integrate the ORT
BeamSearch op with the resulting graphs.

Example command to execute this script:

python convert_to_onnx.py -m openai/whisper-large --output whisper -e

---------

Co-authored-by: Peter McAughan <petermca@microsoft.com>
2023-04-04 05:01:04 -07:00
..
contrib_ops Fix prefast warnings (#15340) 2023-04-03 22:29:13 -07:00
core [QNN EP] Gather support int64 indices input (#15317) 2023-04-03 17:51:42 -07:00
python Whisper Export (#15247) 2023-04-04 05:01:04 -07:00
test [QNN EP] Gather support int64 indices input (#15317) 2023-04-03 17:51:42 -07:00
tool/etw
wasm [js/web] support flag 'optimizedModelFilePath' in session options (#14355) 2023-02-24 15:50:15 -08:00
__init__.py Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings