transcribing chinese audio with the this model, the output text lacks punctuation
#103
by TaoGoblin - opened
When transcribing Chinese audio with the this model, the output text lacks punctuation. How can this be resolved?
Look at the post-processing with GPT-4 section.
But for this task, you can use any LLM. As for me, GPT-4 is not the best post-processor, I like Gemini, but you are not limited.
I also encountered the same problem and asked for a solution