Downloads · 30 days
0
audiosronnx-sidon
TigreGotico/audiosronnx-sidon
audiosronnx-sidon is a machine learning model from TigreGotico. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for audiosronnx. The card lists the license as mit.
ONNX weights for the Sidon speech-restoration engine of audiosronnx. Sidon restores degraded 16 kHz speech and resynthesises it at 48 kHz.
Access
Public
Updated Jul 17, 2026
Repo size
410 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx410 MB · 100%
At a glance
- Library
- audiosronnx
- License
- mit
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- 289a72a4
Model card
From the Hugging Face model README
audiosronnx-sidon
ONNX weights for the Sidon speech-restoration engine of audiosronnx. Sidon restores degraded 16 kHz speech and resynthesises it at 48 kHz.
Two graphs:
feature_extractor.int8.onnx— 8-layer w2v-BERT 2.0 feature predictor (LoRA-adapted), SeamlessM4T log-mel features[1, T, 160]→ hidden states[1, T, 1024]at 50 Hz. Dynamic int8-quantized for CPU.decoder.onnx— DAC vocoder (960× upsample),[1, 1024, T]→[1, 1, 960·T]48 kHz waveform. fp32.
The SeamlessM4T mel front-end runs in numpy inside the adapter, so inference is onnxruntime-only (no torch).
Converted from sarulab-speech/sidon-v0.1 (TorchScript). Graph parity vs. PyTorch: max abs err ≤ 3e-6.
Usage
from audiosronnx import load_sr
sr = load_sr("sidon")
sr.upscale_file("noisy_16k.wav", "restored_48k.wav")
Upstream: sarulab-speech/Sidon (MIT).
- Library
- audiosronnx
- License
- mit
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026