Downloads · 30 days
14
4% of all-time downloads
musicgen-small-onnx
chinedudave06/musicgen-small-onnx
musicgen-small-onnx is a text-to-audio model from chinedudave06. 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 cc-by-nc-4.0.
ONNX export of facebook/musicgen-small with KV-cache decoder for efficient on-device autoregressive generation.
All-time downloads
377
Public
Repo size
6.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx3.7 GB · 100%
At a glance
- Task
- Text-to-Audio
- Library
- onnxruntime
- License
- cc-by-nc-4.0
- Model type
- musicgen
- Access
- Public
- Created
- Mar 16, 2026
- Updated
- Mar 18, 2026
- SHA
- 539611e8
Base models
Model card
From the Hugging Face model README
MusicGen Small — ONNX (KV-Cache)
ONNX export of facebook/musicgen-small with KV-cache decoder for efficient on-device autoregressive generation.
Model Details
| Property | Value |
|---|---|
| Base Model | facebook/musicgen-small |
| Precision | FP32 |
| Audio | Mono (1 channel) |
| Codebooks | 4 |
| Hidden Size | 1024 |
| Sample Rate | 32 kHz |
| Max Length | 1500 steps (~30s) |
| Total Size | ~3.6 GB |
Files
| File | Description | Size |
|---|---|---|
decoder_model.onnx | Step-0 decoder (no KV-cache) | 1.6 GB |
decoder_with_past_model.onnx | Steps 1+ decoder (with KV-cache) | 1.4 GB |
text_encoder.onnx | T5 text encoder | 419 MB |
encodec_decode.onnx | EnCodec audio decoder | 113 MB |
tokenizer.json | T5 tokenizer vocabulary | 2.4 MB |
config.json | Model architecture config | <1 KB |
generation_config.json | Generation parameters | <1 KB |
Usage
These models are designed for the DJNed Android app using ONNX Runtime. The KV-cache decoder pair enables O(1) per-step generation instead of O(n).
Pipeline
- Text encoding:
text_encoder.onnxencodes the text prompt - Step 0:
decoder_model.onnxgenerates the first token + initial KV-cache - Steps 1+:
decoder_with_past_model.onnxgenerates subsequent tokens using KV-cache - Audio decode:
encodec_decode.onnxconverts codebook tokens to audio waveform
License
This model is derived from Meta's MusicGen under the CC-BY-NC-4.0 license.
- Task
- Text-to-Audio
- Library
- onnxruntime
- Type
- musicgen
- License
- cc-by-nc-4.0
- Languages
- en
- Created
- Mar 16, 2026
- Updated
- Mar 18, 2026