Can we get the recognized speech original text from the audio?

[JedLee6]

Dear developers. Could we get the recognized speech original text from the audio in the Qwen2.5-Omni" and "Qwen2-Audio" model? So we can help user to verify if the AI assistant recognized what the user saied correctly? Thanks a lot!

[Juude]

no. for the model used audio directly for input.did not transfer to text first

[github-actions[bot]]

Marking as stale. No activity in 60 days.