Describe the bug
I decoded several files in continuous decoding mode and did a formal WER calculation. To my surprise, the pattern that I see is that half the segments are generally good, and then the other half is "deletion error" in an alternating manner, making to total average error rate above 50%. It appears that the wenet in streaming_mode is missing every alternate segment from the endpointer.

To Reproduce
Steps to reproduce the behavior:

1. run websocket_server_main with TLG decode.
2. Run websocket_client_main --continuous_decoding true <wav_file_with_several_segments>
3. Have manual transcripts of the audio file handy, and hopefully you can figure out from endpointer rules, where it will kick in and cases a new segment.
4. Observe that the transcripts of alternate segments are not returned to the websocket_client_main

Expected behavior
Entire transcripts should be returned.

Screenshots
Let me know if you fail to replicate. I will give you a real example along with an audio file that you can use with gigaspeech model.

Desktop (please complete the following information):

• OS: ubuntu 20
• Browser NA
• Version - cd48b85

Smartphone (please complete the following information):

• Device: [e.g. iPhone6]
• OS: [e.g. iOS8.1]
• Browser [e.g. stock browser, safari]
• Version [e.g. 22]

Additional context
Add any other context about the problem here.