Skip to content

Commit

Permalink
update compare benchmarks
Browse files Browse the repository at this point in the history
  • Loading branch information
guoyongzhi committed Sep 10, 2023
1 parent 159467b commit e491416
Showing 1 changed file with 12 additions and 12 deletions.
24 changes: 12 additions & 12 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -63,21 +63,21 @@ We tested four language identification packages: `LanguageIdentification.jl` (th
We calculated the average accuracy for the languages supported by multiple packages, and the results are as follows:
- tatoeba

| | 50 languages | 39 languages | 35 languages | 24 languages |
|-------------------------------|--------------|--------------|--------------|--------------|
| **LanguageIdentification.jl** | **94.58%** | **94.24%** | **93.77%** | **95.87%** |
| Languages.jl | - | 74.72% | 73.65% | 74.14% |
| LanguageDetect.jl | - | - | 80.81% | 80.61% |
| LanguageFinder.jl | - | - | - | 79.70% |
| | 50 languages | 39 languages | 38 languages | 35 languages | 24 languages |
|-------------------------------|--------------|--------------|--------------|--------------|--------------|
| LanguageIdentification.jl | **94.58%** | **94.24%** | **93.89%** | **93.77%** | **95.87%** |
| Languages.jl | - | 74.72% | - | 73.65% | 74.14% |
| LanguageDetect.jl | - | - | 79.72% | 80.81% | 80.61% |
| LanguageFinder.jl | - | - | - | - | 79.70% |

- wikipedia

| | 50 languages | 39 languages | 35 languages | 24 languages |
|-------------------------------|--------------|--------------|--------------|--------------|
| **LanguageIdentification.jl** | **98.20%** | **98.22%** | **98.09%** | **98.79%** |
| Languages.jl | - | 95.12% | 94.80% | 95.02% |
| LanguageDetect.jl | - | - | 85.49% | 86.23% |
| LanguageFinder.jl | - | - | - | 94.75% |
| | 50 languages | 39 languages | 38 languages | 35 languages | 24 languages |
|-------------------------------|--------------|--------------|--------------|--------------|--------------|
| LanguageIdentification.jl | **98.20%** | **98.22%** | **98.14%** | **98.09%** | **98.79%** |
| Languages.jl | - | 95.12% | - | 94.80% | 95.02% |
| LanguageDetect.jl | - | - | 85.36% | 85.49% | 86.23% |
| LanguageFinder.jl | - | - | - | - | 94.75% |

# Parameter Tuning
You can manually initialize the package using the `LanguageIdentification.initialize` function. By adjusting the parameters, you can achieve different balances between accuracy, speed, and memory usage. The default setting is `ngram=1:4`, `cutoff=0.85`, and `vocabulary=1000:5000`. However, this setting may not be optimal for your specific use case.
Expand Down

2 comments on commit e491416

@guo-yong-zhi
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@JuliaRegistrator register()

@JuliaRegistrator
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Registration pull request created: JuliaRegistries/General/91147

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v1.0.0 -m "<description of version>" e4914167196a7bb9b6c92d57b8eacdccf97c28b0
git push origin v1.0.0

Please sign in to comment.