TTS

#Article #LanguageModel #SpeechProcessing #LongSequence #MultiLingual #OpenWeight
Issue Date: 2025-08-25 VibeVoice-1.5B, microsoft, 2025.08 Comment元ポスト:https://x.com/huggingpapers/status/1959979976536789403?s=46&t=Y6UuIHB0Lv0IpmFAjlc2-Q> Unsupported language – the model is trained only on English and Chinese data; outputs in other languages are unsupported and may be unintelligible or offensive.

日本語は対応していないので注意outputできるspeechのlengthが先行研究より非常に長く、90分近く生成できる模様?

image