Closed bzhangGo closed 2 years ago
@bzhangGo I checked the checkpoint and found it was not the exact one. Now you can fetch the true model via http://lf3-nlp-opensource.bytetos.com/obj/nlp-opensource/neurst/speech_to_text/mustc/de/st_specaug2.tgz.
For how to get the translation output, you can add following configuration into the st_prediction_args.yml:
output_file:
dev: ./dev.hypo.txt
tst-COM: ./tst.hypo.txt
Great! This is very helpful!
Hi all,
I'm trying to reproduce the speech-to-text translation result on MuST-C en-de (22.8 SacreBLEU) as reported in the paper.
I used the given st_specaug checkpoint, and get the following results (commands are given below):
I find that
22.8
is for mixed results rather thantst-COM
. Is there anything I missed during the evaluation? Or, is there any misunderstanding on the evaluation results? Besides, I didn't get the translation output with the above command. Could you please show more details about how to get the model's translation output so as to make translation analysis possible?thanks, Biao