Muyan-TTS：针对播客场景优化的预算为5万美元的可训练文本转语音模型
Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget
AI总结：
本文提出专为播客场景设计的开源可训练TTS模型Muyan-TTS，在5万美元预算内基于超10万小时播客数据预训练，支持零样本高质量语音合成与几十分钟说话人自适应，并提供了完整的数据处理流程、训练程序及优化推理框架。
摘要：
文本转语音（TTS）模型的最新进展是由大语言模型（LLM）的集成所推动的，这增强了语义理解并提升了语音自然度。然而，现有的基于LLM的TTS模型通常缺乏开源训练代码和高效的推理加速框架，限制了其可访问性与适应性。此外，目前没有公开可用的专门针对播客场景优化的TTS模型，而语音交互应用对此有着高度需求。为了解决这些局限性，我们推出了Muyan-TTS，这是一个专为播客应用设计的开源可训练TTS模型，预算在50,000美元以内。我们的模型在超过100,000小时的播客音频数据上进行了预训练，能够实现零样本TTS合成并生成高质量语音。此外，Muyan-TTS支持使用几十分钟的目标语音进行说话人自适应，使其能够针对个人声音进行高度定制。除了将模型开源外，我们还提供了全面的数据收集与处理流程、完整的训练程序，以及一个可加速基于LLM的TTS合成的优化推理框架。我们的代码和模型可在https://github.com/MYZY-AI/Muyan-TTS获取。
英文摘要：
Recent advancements in text-to-speech (TTS) models have been driven by the integration of large language models (LLMs), enhancing semantic comprehension and improving speech naturalness. However, existing LLM-based TTS models often lack open-source training code and efficient inference acceleration frameworks, limiting their accessibility and adaptability. Additionally, there is no publicly available TTS model specifically optimized for podcast scenarios, which are in high demand for voice interaction applications. To address these limitations, we introduce Muyan-TTS, an open-source trainable TTS model designed for podcast applications within a $50,000 budget. Our model is pre-trained on over 100,000 hours of podcast audio data, enabling zero-shot TTS synthesis with high-quality voice generation. Furthermore, Muyan-TTS supports speaker adaptation with dozens of minutes of target speech, making it highly customizable for individual voices. In addition to open-sourcing the model, we provide a comprehensive data collection and processing pipeline, a full training procedure, and an optimized inference framework that accelerates LLM-based TTS synthesis. Our code and models are available at https://github.com/MYZY-AI/Muyan-TTS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
