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

Fix: disabling conditionning on previous text is not working as expected #1224

Merged

Conversation

funboarder13920
Copy link
Contributor

Hello,

prompt_reset_since is set before all_tokens is extended hence does not have the expected effect if I interpret correctly the following description:

condition_on_previous_text: bool
if True, the previous output of the model is provided as a prompt for the next window;
disabling may make the text inconsistent across windows, but the model becomes less prone to
getting stuck in a failure loop, such as repetition looping or timestamps going out of sync.

I also moved the result.temperature > 0.5 condition but I am not sure it should be as it seems to be empirical. Let me know.

@funboarder13920 funboarder13920 changed the title Disabling conditionning on previous text is not working as expected Fix: disabling conditionning on previous text is not working as expected Apr 12, 2023
prompt_reset_since is set before all_tokens is extended hence does not have the expected effect.
@jongwook jongwook merged commit 248b6cb into openai:main May 5, 2023
zackees pushed a commit to zackees/whisper that referenced this pull request May 5, 2023
prompt_reset_since is set before all_tokens is extended hence does not have the expected effect.
ilanit1997 pushed a commit to ilanit1997/whisper that referenced this pull request May 16, 2023
prompt_reset_since is set before all_tokens is extended hence does not have the expected effect.
abyesilyurt pushed a commit to abyesilyurt/whisper that referenced this pull request Nov 13, 2023
prompt_reset_since is set before all_tokens is extended hence does not have the expected effect.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
2 participants