实现毫秒级泰语音素转换，提升语音代理系统响应速度
FastThaiG2P: Lightning-fast Thai Grapheme-to-phoneme Conversion for Voice Agent Pipelines
- 基于词典与规则的快速音素转换框架，支持泰语常用发音规范
- 平均延迟仅0.15毫秒，99.5%词汇可直接查表，剩余0.5%使用回退机制
- 适用于语音合成原型开发，支持CPU上ONNX推理实现4倍实时率
FastThaiG2P 采用 PyThaiNLP 分词、可扩展词典及标准化规则，实现面向文本转语音流水线（国际音标与 Kokoro-TTS 规范）的亚毫秒级泰语字符转音素转换。在包含 27,242 条合成语句的基准测试中，平均延迟为每句 0.15 毫秒，其中 30% 耗时于分词，12% 用于标准化，58% 用于未登录词回退（未登录词率 0.5%）。为验证有效性，我们使用 FastThaiG2P 对包含 20 小时图文对的 Som-TTS 数据集进行音素化，并基于 Kokoro-TTS 配方训练了一个 8200 万参数的 StyleTTS 2 模型。该模型在 CPU 上通过 ONNX 推理以 0.25 实时因子（即 4 倍实时）生成可理解的泰语语音，适合原型与开发阶段使用。
原文摘要 · Abstract (English)
FastThaiG2P provides sub-millisecond Thai grapheme-to-phoneme conversion for text-to-speech pipelines (International Phonetic Alphabet and Kokoro-TTS conventions) using a PyThaiNLP-tokenized, extensible dictionary and normalization rules for common Central Thai speech. The approach achieves an average latency of 0.15 ms per utterance on a benchmark of 27,242 synthetically generated utterances, of which 30\% is spent on tokenization, 12\% on normalization, and 58\% on out-of-vocabulary fallbacks (0.5\% OOV rate). To demonstrate its effectiveness, we used FastThaiG2P to phonemize Som-TTS, an open dataset containing 20 hours of grapheme-and-audio pairs, then trained an 82M-parameter StyleTTS 2 model based on a Kokoro-TTS recipe. The resulting model vocalizes intelligible Thai speech suitable for prototyping and development at 0.25 real-time factor (4x real-time) with ONNX inference on CPU.
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。