Dang Bao Chien

I got the same error when training with librispeech data. I solved the problem by reducing min_output_input_ratio from 0.05 to 0.01. I think removing the sample with the filter function...

> > @chiendb97 > > How many languages have you trained in? How many tokens are there for dictionary size @kaiAksenov I trained with LibriSpeech dataset and dictionary size is...

> There are examples in Sherpa of real-time/streaming/online decoding Can you please specify which example it is? I did look into sherpa repo but did not find any examples about...

> @pkufool @danpovey How I tested was that I read the audio file and evaluated nnet output for the entire audio. Then I used that output to simulate streaming as...

> what version of k2 are you using? see if a newer version helps. I am using the latest version of k2.

> @byshiue I incorrectly typed your name when opening this issue originally. Can you comment on whether there's a workaround for this? It's currently making batch inference effectively useless. @dyoshida-continua...

@QiJune I'm experiencing issues even when using single GPU. If the discrepancies in results are due to varying kernel choices, is there a way to sacrifice some performance in exchange...