Make convert-pt-to-ggml.py backwards compatible with older vocab.json tokenizer files#1001
Merged
ggerganov merged 2 commits intoggml-org:masterfrom Jun 25, 2023
Merged
Conversation
…ransformers whisper tokenizer
ggerganov
approved these changes
Jun 25, 2023
Member
|
Thank you! |
Merged
7 tasks
jacobwu-b
pushed a commit
to jacobwu-b/Transcriptify-by-whisper.cpp
that referenced
this pull request
Oct 24, 2023
….json tokenizer files (ggml-org#1001) * patch checkpoint convert script to keep compatibility with older hf_transformers whisper tokenizer * typo fix
jacobwu-b
pushed a commit
to jacobwu-b/Transcriptify-by-whisper.cpp
that referenced
this pull request
Oct 24, 2023
….json tokenizer files (ggml-org#1001) * patch checkpoint convert script to keep compatibility with older hf_transformers whisper tokenizer * typo fix
landtanin
pushed a commit
to landtanin/whisper.cpp
that referenced
this pull request
Dec 16, 2023
….json tokenizer files (ggml-org#1001) * patch checkpoint convert script to keep compatibility with older hf_transformers whisper tokenizer * typo fix
iThalay
pushed a commit
to iThalay/whisper.cpp
that referenced
this pull request
Sep 23, 2024
….json tokenizer files (ggml-org#1001) * patch checkpoint convert script to keep compatibility with older hf_transformers whisper tokenizer * typo fix
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Patches the script to determine what type of tokenizer files are present and convert appropriately.
Mostly borrows from #725 as a reference. For the same reason mentioned in that PR, converted multilingual checkpoints will continue to exactly match while
.encheckpoints have a 17 byte difference compared to ggml files downloaded by whisper.cpp.The script will also now produce exactly the same files regardless of which type of tokenizer files were used for conversion.