Search papers, labs, and topics across Lattice.
FastThaiG2P achieves sub-millisecond Thai grapheme-to-phoneme conversion, crucial for efficient text-to-speech applications, by employing a PyThaiNLP-tokenized dictionary and normalization rules tailored for Central Thai. The system demonstrates an impressive average latency of 0.15 ms per utterance across a benchmark of over 27,000 synthetically generated samples, with a minimal out-of-vocabulary rate of 0.5%. Utilizing this framework, the authors trained an 82M-parameter StyleTTS 2 model that produces intelligible Thai speech at a rapid 4x real-time speed, showcasing its practical utility in voice agent pipelines.
Achieving phoneme conversion in under 0.15 ms could revolutionize real-time Thai text-to-speech applications.
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.
