Open yv0vaa opened 1 month ago
hey @yv0vaa would you have the time to try out the branch in #1971 and see if it fixes your issues ?
Good afternoon @IlyasMoutawwakil, thanks, but unfortunately it didn't help.
oh.. I just noticed that you're passing max_new_tokens
to the processor and not generate.
Is the behavior different than that of transformers ?
Maybe I'm doing something wrong, but nothing changes. Variation of max_new_tokens in both processor.__call__
and model.generate
does not affect the behavior of the model
System Info
Who can help?
No response
Information
Tasks
examples
folder (such as GLUE/SQuAD, ...)Reproduction (minimal, reproducible, runnable)
Expected behavior
For some reason a final transcript is incomplete and is trimmed in the middle of the speech. I've tried to change max_tokens and max_new_tokens parameter, but nothing has changed. Also I didn't understand how to pass compute type and batch size as parameters. PretrainedConfig and GenerationConfig don't have such parameters. Could anyone help me?