Use tiktoken #1044
Merged
Use tiktoken #1044
Conversation
This file contains 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
Majdoddin
reviewed
Mar 9, 2023
Majdoddin
reviewed
Mar 10, 2023
Co-authored-by: Ruhollah Majdoddin <r.majdodin@gmail.com>
|
I am aware of a university running whisper on powerpc, at least, so their upgrade path will be blocked until tiktoken supports more architectures. |
zackees
pushed a commit
to zackees/whisper
that referenced
this pull request
May 5, 2023
* use tiktoken==0.3.0 * formatting * tuple should be safer * Update whisper/tokenizer.py Co-authored-by: Ruhollah Majdoddin <r.majdodin@gmail.com> * use tiktoken 0.3.1 * reflecting suggestions * cleanup * bypassing load_tiktoken_bpe to avoid blobfile dep --------- Co-authored-by: Ruhollah Majdoddin <r.majdodin@gmail.com>
ilanit1997
pushed a commit
to ilanit1997/whisper
that referenced
this pull request
May 16, 2023
* use tiktoken==0.3.0 * formatting * tuple should be safer * Update whisper/tokenizer.py Co-authored-by: Ruhollah Majdoddin <r.majdodin@gmail.com> * use tiktoken 0.3.1 * reflecting suggestions * cleanup * bypassing load_tiktoken_bpe to avoid blobfile dep --------- Co-authored-by: Ruhollah Majdoddin <r.majdodin@gmail.com>
wsysuper
reviewed
Jul 2, 2023
| vocab_path = os.path.join(os.path.dirname(__file__), "assets", f"{name}.tiktoken") | ||
| ranks = { | ||
| base64.b64decode(token): int(rank) | ||
| for token, rank in (line.split() for line in open(vocab_path) if line) |
There was a problem hiding this comment.
Here, you opened the file and left a unclosed handler.
abyesilyurt
pushed a commit
to abyesilyurt/whisper
that referenced
this pull request
Nov 13, 2023
* use tiktoken==0.3.0 * formatting * tuple should be safer * Update whisper/tokenizer.py Co-authored-by: Ruhollah Majdoddin <r.majdodin@gmail.com> * use tiktoken 0.3.1 * reflecting suggestions * cleanup * bypassing load_tiktoken_bpe to avoid blobfile dep --------- Co-authored-by: Ruhollah Majdoddin <r.majdodin@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Using tiktoken to replace HuggingFace Tokenizers allows faster tokenization and removing tensorflow as a transitive dependency.
A downside is that tiktoken does not yet provide aarch64 linux wheels while tokenizers is built even for ppc64le and s390x. So it may be a blocker for some users..