Downloads · 30 days
0
justinchuby/onnx-genai-example-minimax-music3
onnx-genai-example-minimax-music3 is a text-to-audio model from justinchuby. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. It is set up for onnxruntime. The card lists the license as other.
Public validation package exported from MiniMaxAI/MiniMax-Music3 revision fbdf52fbaaca799592917417eb05f1899f1255ec. It requires the canonical workflow runtime in ONNX GenAI PR 1698 and contains fp16 ONNX neural compon…
Downloads · 30 days
0
Access
Public
Updated Aug 26, 2026
Repo size
25.2 GB
Likes
0
Public
Click a slice to open those files.
.data28.6 GB · 100%
From the Hugging Face model README
Public validation package exported from MiniMaxAI/MiniMax-Music3 revision
fbdf52fbaaca799592917417eb05f1899f1255ec. It requires the canonical workflow
runtime in ONNX GenAI PR 1698 and contains fp16 ONNX neural components, generic
policy graphs, tokenizer assets, and hashless inference_metadata.yaml.
The buffered speech API accepts lyrics in input, music description in
instructions, response_format="wav", and stream=false. Output is 16-bit
PCM stereo WAV at 32 kHz. See LICENSE for redistribution and use terms.
evidence/*_l4.json. The official vocoder
comparison has max absolute error 0.0006339, mean absolute error
0.00008815, and passes atol=rtol=2e-2.evidence/l5_music3_h200.wav — 3.99384375 seconds, 32 kHz,
stereo, RMS 0.1206662, and 99.9683% nonzero samples.Implementation:
<!-- inference-metadata-annotation:start -->Review inference_metadata.annotated.yaml for inline explanations of this package's workflow, tensor/state/cache contracts, and fail-closed omissions. inference_metadata.yaml remains the canonical machine-authored contract; automated validation confirms both files parse to the same metadata object.