Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Need context utterance File #1

Open
vilmavictor opened this issue Feb 22, 2019 · 2 comments
Open

Need context utterance File #1

vilmavictor opened this issue Feb 22, 2019 · 2 comments

Comments

@vilmavictor
Copy link

Hi, could you explain me what is this context utterance file .Is this file need to be created or is there any code available in this repo that will help me generate it. Kindly help me in this issue.
Thank you,

@soraby
Copy link

soraby commented Feb 22, 2019

The context file is an optional dataset that is specified as a parameter for the model, so you don't need it to train a model (see run_tgen.py). Depending on your data, you may be able to provide this file as input if you have some context (mapped to your input data) that would you be useful for your task.

See more information in the paper on the original TGen framework from Dusek. et al:
https://www.sigdial.org/files/workshops/conference17/proceedings/pdf/SIGDIAL22.pdf

TGen framework: https://github.com/UFAL-DSG/tgen

@vilmavictor
Copy link
Author

Thank You for response
I'm trying to generate different personality styles of sentences using Personage. I see that preprocess_da.py helps to create a context file based on the input dataset(csv file). The code requires "mr_cols, text_cols, voice, param_cols". The e2e-challenge dataset that I have, contains only "mr_cols, ref_cols". It would be helpful if you could send me a sample file to use(input file) in this preprocess_da.py and context file that gets generated(output file) from this preprocess_da.py

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants