search

hitachi-speech / EEND

End-to-End Neural Diarization
MIT License
360 stars 57 forks source link

The SA-EEND-EDA experiment DER result on mini_librispeech #20

Closed erichong0318 closed 3 years ago

erichong0318 commented 3 years ago

Excellent code! I have one question that I tried the experiment on egs/mini_librispeech, but I got the DER about 30.34. I choose mini_librispeech due to lack of LDC data,. I directly trained SA-EEND-EDA on mini_librispeech set (set "speaker_num=2" in train.yaml) and then run the infering (also set "speaker_num=2" in infer.yaml) and scoring command. Other conf remain unchanged, so the epoch is 100. I wondering that maybe I did something wrong. If you have already tried this experimet on mini_librispeech, can you tell me about your final DER on mini_librispeech? I want to know whether I done this experiment correct or not. Thanks a lot!!

speaker-lover commented 3 years ago

I have the same problem. Have you solved it?

erichong0318 commented 3 years ago

What's the trouble you meet?

yfchen97 @.***> 於 2021年6月15日 週二 上午9:45寫道：

I have the same problem. Have you solved it?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/hitachi-speech/EEND/issues/20#issuecomment-861107258, or unsubscribe https://github.com/notifications/unsubscribe-auth/AR3IGOOJTTMEOXN4LHUYZ4DTS2WFDANCNFSM444Z4AOQ .

shota-horiguchi commented 3 years ago

I got 29.84% DER, so there's probably nothing wrong with your experiments.