TinyAudio is introduced, a compact flow-matching-based TTA model for low-resource deployment that achieves competitive generation quality on AudioCaps and TTA-Bench and demonstrates a practical quality-footprint trade-off for low-resource TTA deployment.
Abstract
Text-to-audio (TTA) generation has advanced rapidly in generation quality and instruction following. However, representative systems often require around a billion parameters, limiting deployment on resource-constrained devices. This paper introduces TinyAudio, a compact flow-matching-based TTA model for low-resource deployment. At its core, TinyAudio uses TA-DiT, a 35M single-stream flow-matching Transformer. TinyAudio also includes TA-CLAP, a 32M audio-aligned text encoder, and TA-VAE, whose 20M decoder reconstructs 44.1 kHz audio from compressed latents. TinyAudio has only 87M parameters in total, over 90% fewer than representative billion-parameter pipelines, and uses 0.48 GB peak GPU memory. TinyAudio achieves competitive generation quality on AudioCaps and TTA-Bench. We further introduce TinyAudio-MF, a MeanFlow-accelerated model that enables real-time generation with a four-core CPU quota. Our results demonstrate a practical quality-footprint trade-off for low-resource TTA deployment.
An architecture-aware inference stack that combines guarded W8A8 and fused operators, padded-text compaction, and modality-aware sparse attention while preserving dense cross-modal and text-conditioning paths is developed.
Xiao-Da Yang, Yu-Xian Liu, Kaiwen Zheng et al.· 0 citations
Experiments show that ZipCodec substantially outperforms existing streaming codecs at comparable bitrates in both reconstruction and downstream tasks, while operating at a significantly lower frame rate.
Luca Della Libera, Cem Subakan, M. Ravanelli· 0 citations
Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent speech-enhancem...
X-Pred MeanFlow is proposed, a few-step streaming token-to-mel decoder that reparameterizes MeanFlow with mel-space prediction and introduces layer-selective block-wise attention to enable continuous chunk-wise generation with bounded context.
Han-Ke Xie, Xia-Ming Ren, Qi-Rui Zhan et al.· 0 citations
This work proposes RVQ position aware speculative decoding for the MultiCodeDecoder, and delivers 2 to 2.2x speedup for RVQ token generation with Qwen3-TTS 0.6B on recent iPhone and Apple Silicon Mac devices.
Berkin Durmus, Eduardo Pacheco, Zach Nagengast et al.· 0 citations
We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid attention architecture with X-MTP, a lightweight shared-KV multi-token prediction design that eliminates per-depth KV-cache replay and employs a lightweight verification head for rollback-...
Chang-Di Yang, Feng-Quan Jiao, Hao-Chih Lin et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.