songtaoshi
songtaoshi
Dear Dr Zhang, Thanks for reading my message !!! I am really impressed and thankful to your fantastic book!!!! I think this book will **change my life** because I have...
and also I see the training code, the LM input ys is the same as the target ys. This should not be +text as input; text+ as output?
why i have to config the workers to be 0?
@h-jia hello I have also met the same problem, have you solved this problem
I met this problem not finding _k2. I found that `pip install` directly install the py39 k2 and my python version is py37. Then I specify the py37 k2 and...
Maybe I am late and not quite understanding the context, but I think you can just use pyaudio get the stream and push it into your ASR service.
my torch version is 1.6.0. cuda 10.2