Saurabh Barge comments

Results 3 comments of


                                            Saurabh Barge

Performance discrepancy in WER between decoding parallelly and decoding with single thread for non-streaming zipformer model

Yes, I decoded this audio file https://www.voiptroubleshooter.com/open_speech/american.html, "OSR_us_000_0011_8k.wav" using the zipformer-small pretrained model https://huggingface.co/Zengwei/icefall-asr-librispeech-zipformer-small-2023-05-16 Following are the commands I used for decoding: **starting pretrained model server:** ``` ./bin/sherpa-onnx-offline-websocket-server \ --port=8894...

Performance discrepancy in WER between decoding parallelly and decoding with single thread for non-streaming zipformer model

did anybody had a chance to look into it?

Performance discrepancy in WER between decoding parallelly and decoding with single thread for non-streaming zipformer model

okay, I think that since we are not able to pass bpe-model when starting the offline-websocket server, the results are worse with `offline-websocket-client-decode-files-paralell.py` compared with `offline-decode-files.py` where we are able...