Open bertfrees opened 1 month ago
Modifying EuroSentenceDetector
in order to make it split on e.g. ";" in addition to "." would be a possible solution for this issue, but it might not be semantically correct anymore to call the result "sentences".
Another approach could be to make it the responsibility of GoogleRestTTSEngine
to split the SSML into smaller parts if this error is encountered, similar to how DefaultSSMLMarkSplitter
does it.
Occasionally, Google Cloud TTS returns the following error:
Since sentence detection is currently done based on ".", it could indeed happen that sentences are very long, e.g. if they contain a lot of commas, colons and/or semicolons.