Perth ONNX
Audio watermarking export
1 min readupdated
This is an ONNX export (a format for running models efficiently) of Resemble AI's Perth invisible audio watermarker. It lets you imperceptibly embed watermarks into audio frequencies below 2 kHz and reliably detect them across the entire clip. The model weights remain completely identical to the original, and the graphs package the full pipeline, including STFT (Fourier transform) and inverse transform steps. This tool is built for audio system developers, researchers, and anyone looking to protect audio content.
Key features
- Ready-to-use
perth_embed.onnxandperth_detect.onnxmodels in ONNX format for watermark embedding and detection. - Exact parity with the original PyTorch implementation (maximum absolute difference is less than 5.5e-7).
- Built-in STFT and inverse STFT stages inside opset 18 graphs.
- Support for mono audio at a 32 kHz sampling rate.
What you can do
- Embed an invisible watermark into audio recordings using the
perth_embed.onnxgraph. - Check an audio clip for a watermark and get a confidence score from 0 to 1 via
perth_detect.onnx. - Integrate audio content verification into third-party pipelines without a PyTorch dependency.
Example
Input for embedding: 32 kHz mono audio in float32 format. Output: an audio clip with the embedded marker.
Read more
DetailsFormat: ONNX (opset 18)
Base model: Resemble AI Perth
License: MIT










Comments