Downloads · 30 days
40
22% of all-time downloads
soniqo/Supertonic-3-ONNX-INT8
Supertonic-3-ONNX-INT8 is a text-to-speech model from soniqo. Use it when you need text read aloud. It is set up for onnx. The card lists the license as openrail.
Dynamic int8 quantization of Supertone/supertonic-3 for low-memory on-device inference. Same 4-graph non-autoregressive flow-matching pipeline (durationpredictor → textencoder → vectorestimator ×N → vocoder), 31 langu…
Downloads · 30 days
40
22% of all-time downloads
All-time downloads
181
Public
Repo size
102 MB
Likes
4
Public
Click a slice to open those files.
.onnx102 MB · 97%
From the Hugging Face model README
Dynamic int8 quantization of Supertone/supertonic-3 for low-memory on-device inference. Same 4-graph
non-autoregressive flow-matching pipeline (duration_predictor → text_encoder → vector_estimator ×N → vocoder), 31 languages, 44.1 kHz, ONNX Runtime — just smaller and lighter.
onnxruntime.quantization.quantize_dynamic (QInt8); activations fp32.onnx/{duration_predictor,text_encoder,vector_estimator,vocoder}.onnx (int8) · onnx/tts.json ·
onnx/unicode_indexer.json · voice_styles/*.json (10 voices) · config.json · LICENSE.
Drop-in for the supertonic package via model_dir, or run the
4 graphs directly with ONNX Runtime. The text front-end is G2P-free (NFKD + unicode_indexer.json
lookup — no espeak/phonemizer).
Derivative of Supertone/supertonic-3 (commit 3cadd1ee6394adea1bd021217a0e650ede09a323) by Supertone, Inc. (paper
arXiv:2503.23108). Licensed under BigScience OpenRAIL-M — the
upstream use-based restrictions carry over (no non-consensual impersonation/deepfakes, no undisclosed
machine-generated content, etc.) and must pass through to downstream users. This card marks it a modified
(quantized) artifact per the license. The original LICENSE is included.
TTSInterface ONNX model.