Binbin Zhang

Yes, ITN, punctuation is in our plan, and the solution should be simple and elegant.

> Moree data augment like rir > > [pytorch/audio#2624](https://github.com/pytorch/audio/issues/2624) > > torchaudio will add multi channel riri  based on pyroomacoustics Great!

please paste the error message

Did you try to debug? @pengzhendong please follow the issue.

I have no idea. There is no such problem in our practice.

I'm not sure. I think you can try to add the language one by one to figure out the problem.

Did you get right result when decoding without LM?

010010007 yd y yeh y yew yea y yeo 010010041 yi yea yeh yt zoe 010010064 yd y yeh yi qr yea yea yi qgh yi 010010093 yt yea zoe...

what's you pytorch version and libtorch version?

We update both the pytorch and libtorch to 1.10.0, please pull the latest code and retry.