Skip to content
Other

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.onnx and perth_detect.onnx models 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.onnx graph.
  • 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 moreDetails
Format: ONNX (opset 18)
Base model: Resemble AI Perth
License: MIT
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # codebucketsolutions/perth-onnx
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download codebucketsolutions/perth-onnx --local-dir ~/models/perth-onnx
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to perth-onnx
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Perth (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

codebucketsolutions/perth-onnx
Author
codebucketsolutions
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments