CoolFace
Modelpublic

JustACluelessKidAtSchool/magenta-rt-2-qad-onnx

sourceHugging Faceapache-2.0updated 21d agoView on Hugging Face
1likes
Model Card

Magenta RT 2 — Quantized Acoustic Distillation (QAD) ONNX

This repository hosts the Quantized Acoustic Distillation (QAD) ONNX models for real-time neural music generation in the browser via WebGPU and WASM SIMD.

Architecture & Model Components

  1. 1.`authentic_student_generator_int8.onnx` (64.0 MB):
  2. 2.Unrolled 12-codebook Depthformer student model (6 temporal layers, 2 depth layers, 35.7M active parameters).
  3. 3.Generates 12 hierarchical Residual Vector Quantizer (RVQ) acoustic codes causally per 40 ms frame in ~39 ms on CPU (~12 ms on WebGPU).
  4. 4.Conditioned on 768-dim MusicCoCa style embeddings and 128-element MIDI chord/note vectors.
  1. 1.`authentic_spectrostream_decoder_int8.onnx` (41.9 MB):
  2. 2.Full 35.6M-parameter SpectroStream neural vocoder.
  3. 3.Converts 12 RVQ codes into 48 kHz stereo PCM audio via convolutional frame expansion, harmonic synthesis, and WebGPU/WASM-native MatMul IDFT overlap-add.
  1. 1.`style_embeddings.json` (144 KB):
  2. 2.Precomputed 768-dimensional latent style vectors across curated genres: Lo-Fi, Chill-Hop, Smooth Jazz, Synthwave, Deep Ambient, Classical, Rock, Funk, and Cinematic.

Direct CDN & Download Links

  • —authentic_student_generator_int8.onnx: https://huggingface.co/JustACluelessKidAtSchool/magenta-rt-2-qad-onnx/resolve/main/authentic_student_generator_int8.onnx
  • —authentic_spectrostream_decoder_int8.onnx: https://huggingface.co/JustACluelessKidAtSchool/magenta-rt-2-qad-onnx/resolve/main/authentic_spectrostream_decoder_int8.onnx
  • —style_embeddings.json: https://huggingface.co/JustACluelessKidAtSchool/magenta-rt-2-qad-onnx/resolve/main/style_embeddings.json

In-Browser Deployment

Designed for 100% client-side zero-backend browser execution in:

  • —`music_studio.html`: Interactive live jam studio with prompt latent surface and keyboard steering.
  • —`focus_radio.html`: Continuous endless AI radio stream with ambient soundscape mixer.
  • —Models are cached into browser IndexedDB (CascadeOfflineMusicDB) on first download for permanent offline execution.