构建台湾 Mandarin 口语语言模型：首次尝试
Building a Taiwanese Mandarin Spoken Language Model: A First Attempt
AI总结：
本文首次尝试构建面向台湾 Mandarin 的端到端口语大语言模型，采用仅解码器 Transformer 架构并支持全双工实时多轮语音交互，同时提出合成对话数据训练方案与对话流畅性评估平台。
摘要：
本技术报告介绍了我们构建台湾 Mandarin 口语大语言模型（LLM）的初步尝试，该模型专门用于在多轮对话中实现实时语音到语音交互。我们的端到端模型采用仅解码器 Transformer 架构，旨在实现无缝交互，同时保持对话流畅性，包括支持同时说话和聆听的全双工能力。本文还详细介绍了训练过程，包括使用合成对话进行数据准备以及针对实时交互的调整。我们还开发了一个平台，用于评估多轮对话中的对话流畅性和响应连贯性。我们希望本报告的发布能为未来台湾 Mandarin 口语 LLM 的发展做出贡献。
英文摘要：
This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations. Our end-to-end model incorporates a decoder-only transformer architecture and aims to achieve seamless interaction while preserving the conversational flow, including full-duplex capabilities allowing simultaneous speaking and listening. The paper also details the training process, including data preparation with synthesized dialogues and adjustments for real-time interaction. We also developed a platform to evaluate conversational fluency and response coherence in multi-turn dialogues. We hope the release of the report can contribute to the future development of spoken LLMs in Taiwanese Mandarin.
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。
