Closed shaynemei closed 1 year ago
Could you make it a command line argument?
Could you make it a command line argument?
Done, set default to 1.0
Thanks!
I am surprised 0.3 secs is not enough, is there anything about Sherpa that explains this?
On Fri, Sep 1, 2023, 8:48 AM Fangjun Kuang @.***> wrote:
Merged #472 https://github.com/k2-fsa/sherpa/pull/472 into master.
— Reply to this email directly, view it on GitHub https://github.com/k2-fsa/sherpa/pull/472#event-10251819542, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAZFLO4ZUMFBJ66Y4RZPJCTXYEWF7ANCNFSM6AAAAAA4GSF3YI . You are receiving this because you are subscribed to this thread.Message ID: @.***>
@shaynemei
Which streaming model are you using and have you tried other values between [0.3, 1.0]?
this is the model I used to run the evaluation: https://huggingface.co/Zengwei/icefall-asr-librispeech-streaming-zipformer-2023-05-17
I've also tried 0.5 on some of the problematic utterances (didn't run full evaluation for WER), and got a little bit more BPE units at the end but still missing one or two BPE units.
Original tail padding is not long enough which causes worse performance compared to icefall decoding:
for example in the tedlium_dev evaluation:
Increasing the padding from 0.3 to 1.0 seems to bring the WER back to the same as icefall: