Skip to content

Conversation

@sssshhhhhh
Copy link
Contributor

@sssshhhhhh sssshhhhhh commented Jan 31, 2026

Check token ids instead of magic numbers on vocab size. Values are same for all 3 openai tokenizer variations

@jordimas
Copy link
Collaborator

jordimas commented Feb 1, 2026

Thanks, more robust approach

@jordimas jordimas merged commit 57c053a into OpenNMT:master Feb 1, 2026
17 checks passed
@sssshhhhhh sssshhhhhh deleted the whisper branch February 1, 2026 12:10
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

Successfully merging this pull request may close these issues.

2 participants