About the "input length mismatch" bug in torchaudio's RNNT loss

[Zain-Jiang]

In conformer/convolution.py, line 183, the code

output_lengths = input_lengths >> 2
output_lengths -= 1

when the result of input_lengths >>2 is xx.75, the torchaudio.transforms.RNNTLoss will raise "input length mismatch" Error. Maybe this is a bug when calculating the output lengths, I'm not sure of it.

[longlnOff]

I've gotten same problem. Have you fixed that yet?