Text feature extraction using SpeechLM

[wonjune-kang]

Hello, thank you for your great work on this repo!

I'm interested in using SpeechLM to produce text representations in addition to speech representations. Is there a simple way of doing this, similar to the code snippet that you provide here for speech representations? I found the forward_text function which seems like it should be doing this, but I couldn't figure out a way to easily produce src_tokens to feed in there.

Thank you!