About Word Error

[jerrymatjila]

Thank you for the paper and code.

Voice cloning is excellent, however, for text to speech I'm experiencing word errors. Here is an example

Prompt audio file

Transcript: "This comprehensive set of behaviors allows for a human-like speech synthesis system, capable of mimicking the complex vocal patterns observed in natural human conversations."

Language: en

Output: audio output

Any ideas and plans to fix this?