OpenNMT Forum

Unable to get Output while running the pretrained document summarization transformer model

I am using the approach given in “Simple-Opennmt-py-Rest server

As shown in image when I run the given command:-curl -i -X POST -H “Content-Type: application/json” -d @data.json

I get the following output:-[[{“n_best”:1,“pred_score”:-12.024673461914062,“src”:“so far no videos were used in the crash investigation . ‘’ he added , a person who has such a video needs to immediately give it to the investigators . '' robin 's comments follow claims by two magazines , german daily bild and french paris match , of a cell phone video showing the harrowing final seconds from on board germanwings flight 9525 as it crashed into the french alps . all 150 on board were killed . paris match and bild reported that the video was recovered from a phone at the wreckage site . the two publications described the supposed video , but did not post it on their websites . the publications said that they watched the video , which was found by a source close to the investigation . one can hear cries of ` my god ’ in several languages , ‘’ paris match reported . `` metallic banging can also be heard more than three times , perhaps of the pilot trying to open the cockpit door with a heavy object . towards the end , after a heavy shake , stronger than the others”,“tgt”:""}]]

As shown in above output the tgt or the summarized document is empty.The src is the input text given by me.

How can I get the summarized file in the tgt?What I an doing wrong?
What Tokenizer should I use in conf.json in available_models folder?
Please help ASAP.

Do you get a proper output using the file translation script ( or onmt-translate if installed via pip)?

Yes when I ran on google colab using onmt translate it outputed correct predictions.

A simple inference on your input indeed yields an empty output.
This model seems very sensitive to some specific parameters at inference. See here.
You need to add those in your server configuration.