用RNN架构的RWKV-7实现更快更省的语音合成
RWKVTTS: Yet another TTS based on RWKV-7
- 基于RWKV-7 RNN架构，替代传统Transformer提升效率
- 合成速度更快，资源消耗更低，语音自然度更高
- 适合低资源环境，推动语音合成普惠化
人机交互依赖直观高效的接口，其中语音因其自然性与易用性尤为突出。近期基于Transformer的文本到语音（TTS）系统，如Fish-Speech、CosyVoice和MegaTTS 3，在质量与真实感上取得显著进步，推动了TTS领域的发展。本文介绍一种面向TTS应用的新型RNN架构——RWKV-7 \\cite{peng2025rwkv}。与传统Transformer模型不同，RWKV-7利用循环神经网络的优势，在保持高质量输出的同时，实现更高的计算效率与可扩展性。全面基准测试表明，其在合成速度、语音自然度及资源效率等多个关键指标上优于基于Transformer的模型。此外，我们探索其在多样语言场景与低资源环境中的适应能力，展示了其在普及语音合成技术方面的潜力。这些发现使RWKV-7成为一项强大且创新的替代方案，为实际应用中更便捷、更通用的语音合成铺平道路。代码与权重已开源：https://github.com/yynil/RWKVTTS, https://huggingface.co/spaces/RWKV-Red-Team。
原文摘要 · Abstract (English)
Human-AI interaction thrives on intuitive and efficient interfaces, among which voice stands out as a particularly natural and accessible modality. Recent advancements in transformer-based text-to-speech (TTS) systems, such as Fish-Speech, CosyVoice, and MegaTTS 3, have delivered remarkable improvements in quality and realism, driving a significant evolution in the TTS domain. In this paper, we introduce RWKV-7 \cite{peng2025rwkv}, a cutting-edge RNN-based architecture tailored for TTS applications. Unlike traditional transformer models, RWKV-7 leverages the strengths of recurrent neural networks to achieve greater computational efficiency and scalability, while maintaining high-quality output. Our comprehensive benchmarks demonstrate that RWKV-7 outperforms transformer-based models across multiple key metrics, including synthesis speed, naturalness of speech, and resource efficiency. Furthermore, we explore its adaptability to diverse linguistic contexts and low-resource environments, showcasing its potential to democratize TTS technology. These findings position RWKV-7 as a powerful and innovative alternative, paving the way for more accessible and versatile voice synthesis solutions in real-world applications.Our code and weights are https://github.com/yynil/RWKVTTS, https://huggingface.co/spaces/RWKV-Red-Team
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。