I'm trying to get tortoise-tts to pronounce acronyms correctly. Example of text that I'd like tortoise-tts to generate an audio file for: OpenAI ChatGPT is a new language model.
The audio file generated by tortoise-tts is: OpenAI Chat is a new language model (GPT is missing from the audio file).
I can replace ChatGPT with Chat gee pee tee but I've had a case where the jee pee tee changes the tone of the audio file.
Questions:
- Is replacing
ChatGPTwithChat gee pee teethe most optimal solution? - If it is the most optimal solution, is there any convenient script to replace acronyms with their pronounced version (GPT->jee pee tee)?
- If it is not the most optimal solution, what is the most optimal solution?