| --- |
| tags: |
| - text-classification |
| - language-identification |
| inference: false |
| license: cc-by-sa-3.0 |
| language: multilingual |
| library_name: staticvectors |
| base_model: |
| - NeuML/language-id |
| --- |
| |
| # Language Detection with StaticVectors |
|
|
| This model is an export of this [FastText Language Identification model](https://fasttext.cc/docs/en/language-identification.html) for [`staticvectors`](https://github.com/neuml/staticvectors). `staticvectors` enables running inference in Python with NumPy. This helps it maintain solid runtime performance. |
|
|
| Language detection is an important task and identification with n-gram models is an efficient and highly accurate way to do it. |
|
|
| _This model is a quantized version of the [base language id model](https://hf.co/neuml/language-id). It's using 2x256 Product Quantization like the original quantized model from FastText. This shrinks this model down to 4MB with only a minor hit on accuracy._ |
|
|
| ## Usage with StaticVectors |
|
|
| ```python |
| from staticvectors import StaticVectors |
| |
| model = StaticVectors("neuml/language-id-quantized") |
| model.predict(["What language is this text?"]) |
| ``` |
|
|
