You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
the answer is in the riva container log. basically it doesn't like sentences.
E0429 19:38:13.568981 102 tts-preprocessor.cc:96] preprocessor had an errorSSML Input does not currently support split on sentence. Input text too long.The text-to-speech TTS pipeline implemented for the Riva TTS service is based on a two-stage pipeline. Riva first generates a mel-spectrogram using the first model, and then generates speech using the second model. This pipeline forms a TTS system that enables you to synthesize natural sounding speech from raw transcripts without any additional information such as patterns or rhythms of speech.
the readaloud project makes effort to clean up input, but riva can't handle this input without throwing an error, why?
The text was updated successfully, but these errors were encountered: