Availability of trained models

Question

Availability of trained models

rahular opened this issue 7 years ago · comments

Hi, first of all, thank you for open sourcing the code base. In the README you mention that Paragraph-level model and sentence-level model will be made available soon.

Can you give a rough timeframe of when these models will be made available?

Fariz Rahman commented 6 years ago

sentence

Fariz Rahman · Answer 1 · Mon Nov 20 2017 12:50:59 GMT+0800 (China Standard Time)

Trained sentence model (15 epochs)
https://drive.google.com/file/d/16Gi1oZr3mEGMEUCsOQ3whFfDlv8IAyzG/view?usp=sharing

Rahul A R · Answer 2 · Mon Nov 20 2017 14:45:04 GMT+0800 (China Standard Time)

@farizrahman4u thanks. Is this for sentence or paragraph level?

Buraka · Answer 3 · Thu Nov 29 2018 13:20:14 GMT+0800 (China Standard Time)

@farizrahman4u Is this a torch model?, i have tried loading in pytorch, and i am facing this error
T7ReaderException: unknown type id 32. The file may be corrupted.
Can you guide me to how to load it ?

Hamza Lebbar · Answer 4 · Tue Mar 19 2019 00:05:40 GMT+0800 (China Standard Time)

First copy the trained model to sentence/model.
Then Inside the sentence folder run: th translate.lua -model model/<model file name> -config config-trans . You have to change <model file name> with the name of the trained model and in config-trans change src=../data/processed/src-dev.txt to src=path_to_your_input_sentence_text_file
You normally will get the result printed out on the terminal after running the command.