Transformers
PyTorch
English
whisper
Eval Results
Inference Endpoints

Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'.

#4

Hey MU-NLPC 👋,

Your model repository seems to contain outdated generation config parameters, such as 'max_initial_timestamp_index' and is missing the 'prev_sot_token_id' parameter. These parameters need to be updated to correctly handle long-form generation as stated in as part of https://github.com/huggingface/transformers/pull/27658. This PR makes sure that everything is up to date and can be safely merged.

Best, the Transformers team.

hajekad changed pull request status to merged
NLP Centre, Faculty of Informatics, Masaryk University org

Hi @patrickvonplaten ,
thank you for your merge request, we appreciate it and we merged the changes. If you have any updates in the future, don't hesitate to let us know, we will be happy to hear from you. Thanks!

Sign up or log in to comment