7 items • Updated • 3
Model exported using torch.onnx.export of openai whisper models and set static shapes for seq_len
To run the model Refer to Ryzen AI support for whisper.cpp
Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for amd/whisper-base-onnx-npu
Base model
openai/whisper-base