Download Latest Version
v0.4.6 source code.tar.gz (299.3 kB)
Get an email when there's a new version of Evaluate
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2025-06-20 | 1.3 kB | |
| v0.4.4 source code.tar.gz | 2025-06-20 | 297.9 kB | |
| v0.4.4 source code.zip | 2025-06-20 | 543.5 kB | |
| Totals: 3 Items | 842.7 kB | 2 | |
Bug fixes
- support jiwer 4.0 by @lhoestq in https://github.com/huggingface/evaluate/pull/685
- Fix Perplexity Score For Tokenizers without bos_token_id by @kylehowells in https://github.com/huggingface/evaluate/pull/682
- Fix size attribute error for precision/recall/f1 by @Maxwell-Jia in https://github.com/huggingface/evaluate/pull/656
Other changes
- Add required hf_token secret to build main documentation by @albertvillanova in https://github.com/huggingface/evaluate/pull/635
- Pin numpy<2 as required by tensorflow to fix doc building by @albertvillanova in https://github.com/huggingface/evaluate/pull/631
- Support nltk>=3.9 to fix vulnerability by @albertvillanova in https://github.com/huggingface/evaluate/pull/629
- add tip in docs and readme referring to lighteval by @MoritzLaurer in https://github.com/huggingface/evaluate/pull/618
New Contributors
- @MoritzLaurer made their first contribution in https://github.com/huggingface/evaluate/pull/618
- @Maxwell-Jia made their first contribution in https://github.com/huggingface/evaluate/pull/656
- @kylehowells made their first contribution in https://github.com/huggingface/evaluate/pull/682
Full Changelog: https://github.com/huggingface/evaluate/compare/v0.4.3...v0.4.4
