Project description

bleuscore

bleuscore is a fast(maybe:) bleu score calculator base on Rust.

Quick Start

The usage is exactly same with huggingface evaluate:

- import evaluate
+ import bleuscore

predictions = ["hello there general kenobi", "foo bar foobar"]
references = [
    ["hello there general kenobi", "hello there !"],
    ["foo bar foobar"]
]

- bleu = evaluate.load("bleu")
- results = bleu.compute(predictions=predictions, references=references)
+ results = bleuscore.compute(predictions=predictions, references=references)

print(results)
# {'bleu': 1.0, 'precisions': [1.0, 1.0, 1.0, 1.0], 'brevity_penalty': 1.0, 
# 'length_ratio': 1.1666666666666667, 'translation_length': 7, 'reference_length': 6}

Project details

These details have not been verified by PyPI

Project links

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Release history Release notifications | RSS feed

0.1.3

May 27, 2024

0.1.2

Apr 29, 2024

0.1.1

Apr 26, 2024

This version

0.1.0

Apr 23, 2024

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bleuscore-0.1.0.tar.gz (16.9 kB view hashes)

Uploaded Apr 23, 2024 Source

Built Distributions

bleuscore-0.1.0-cp38-abi3-win_amd64.whl (713.6 kB view hashes)

Uploaded Apr 23, 2024 CPython 3.8+ Windows x86-64

bleuscore-0.1.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.7 MB view hashes)

Uploaded Apr 23, 2024 CPython 3.8+ manylinux: glibc 2.17+ x86-64

bleuscore-0.1.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl (1.7 MB view hashes)

Uploaded Apr 23, 2024 CPython 3.8+ manylinux: glibc 2.5+ i686

bleuscore-0.1.0-cp38-abi3-macosx_11_0_arm64.whl (826.3 kB view hashes)

Uploaded Apr 23, 2024 CPython 3.8+ macOS 11.0+ ARM64

bleuscore-0.1.0-cp38-abi3-macosx_10_12_x86_64.whl (874.7 kB view hashes)

Uploaded Apr 23, 2024 CPython 3.8+ macOS 10.12+ x86-64

Hashes for bleuscore-0.1.0.tar.gz

Hashes for bleuscore-0.1.0.tar.gz
Algorithm	Hash digest
SHA256	`f7fdee89d35334581f2b476022c0010cfe08e2ac54ba5dd71402f438115afed3`
MD5	`0e45e939eec9b9fab1bf71772e1eb1c8`
BLAKE2b-256	`618cb455fefac23822143a29b64773fc3a45de69873c46f1f52f68752755f46e`

Hashes for bleuscore-0.1.0-cp38-abi3-win_amd64.whl

Hashes for bleuscore-0.1.0-cp38-abi3-win_amd64.whl
Algorithm	Hash digest
SHA256	`eb6c9b33f0aca9f5b78c6800433c53db7de3ee81bb49c69f265d6364fd12dd2c`
MD5	`1425d98f3bb2d373ce0ed1338afffccd`
BLAKE2b-256	`5336178130616fab4c3286feb08f3de55f5a422fdb071baf83b7ff577e0fe74a`

Hashes for bleuscore-0.1.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for bleuscore-0.1.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`d1e677ce59eb091b8e214d6f6dd3920ee79e268f25bc9928186cadb9ab9458b4`
MD5	`2f90dcd94694c1d4e624c6b0992fc4ca`
BLAKE2b-256	`4c26efb190d33bea7a603be727aebcbdcac68ca590583d636b954515bdc47b0f`

Hashes for bleuscore-0.1.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl

Hashes for bleuscore-0.1.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm	Hash digest
SHA256	`a7795cf1c2ecba45136e9c41aee173a43832d06e3b578350f2963dc5f59f5d24`
MD5	`3025b98ce699453baca41b146c0177c1`
BLAKE2b-256	`38f787ef13fa101628a98da0ed1b854b7318b1a7869c26a30fad25a275b9049a`

Hashes for bleuscore-0.1.0-cp38-abi3-macosx_11_0_arm64.whl

Hashes for bleuscore-0.1.0-cp38-abi3-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`4b540a62a0c93dbefad9de88d00fdf3accd8211dd16c7a66bb14648debcf9c1c`
MD5	`94cab4ec423da30f6728b70e27beca97`
BLAKE2b-256	`4d6db4e00524f4e4e1ed41a02b1af5eb9b68cec39537fe8ea436cc46414bb7d9`

Hashes for bleuscore-0.1.0-cp38-abi3-macosx_10_12_x86_64.whl

Hashes for bleuscore-0.1.0-cp38-abi3-macosx_10_12_x86_64.whl
Algorithm	Hash digest
SHA256	`0a07a25fd5af947a2cf10fb7f554b6bb9e549739bc728457cd1e858a379f362f`
MD5	`2a84db6ae319e138aebad712c0f91cfb`
BLAKE2b-256	`622f6b205588f3c24d54c2383fa6e00d444b48ea1548aac78b10f6df725d78ff`