AI & ML
ZONOS3-Mini Technical Report
arXiv cs.SD0 views
arXiv:2611.16525v2 Announce Type: replace Abstract: ZONOS3-Mini is an ultra-compact, ultra-fast, zero-shot voice-cloning TTS model. The model can run in real time on a laptop or smartphone. For its latency and size, it achieves state-of-the-art accuracy and cloning fidelity. To achieve this we propose a latent MoE backbone with only 886M parameters (100M active per token) and a new audio codec, Zyphra Audio Codec 1 (ZAC-1), which represents 44.1 kHz audio at a 15 Hz frame rate. On the new ZTTS2-Eval benchmark, ZONOS3-Mini reaches a 6.71% macro-average WER over 55 language sets (35 clean and 20 in the wild), which is competitive with larger and slower state-of-the-art models. We release the model weights, inference, and training code.
Source:https://arxiv.org/abs/2611.16525PreviousMarimba: A System One Model for SpeechNextThe Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
Related posts
AI-Native Development Framework for European Public Organisations (AI SDLC - Model-Adaptive)
0dev.to Machine Learning
How to Trim Audio for a Fundraiser Video — Free, in Your Browser
0dev.to Tutorial
WARN Act and Layoffs in Grocery Stores: What Supermarket Workers Should Know
0dev.to Career
How to Handle "Not Interested" on a Cold Call: Cold Calling Tips and Sales Scripts for SDRs and Founders
0dev.to Career
How to Choose the Best Web Design Company for Your Business
0dev.to Career
The Government’s New EV Mandate: What Doubling the Staff Car Cap Means for Auto Stocks
0dev.to Beginners