Edit model card

1.Model Description

Hailay/GeezScriptTokenizer: is a language-specific tokenizer developed to handle the unique characteristics of Geez script languages, particularly Amharic and Tigrinya. This tokenizer is designed to effectively manage the complexities of these languages by accurately identifying and processing prefixes, postfixes, and word boundaries within the text. By incorporating these language-specific rules, GeezScriptTokenizer significantly improves tokenization efficiency, ensuring better representation and performance for tasks involving Amharic and Tigrinya.

This tokenizer is highly suited for natural language processing (NLP) tasks where standard multilingual tokenizers may struggle with the nuances of Geez script languages. Hailay/GeezScriptTokenizer is an ideal tool for researchers and developers working with these languages, providing a tailored approach to tokenization that enhances the overall quality of language models and downstream tasks.

##2. How To Use # To use Hailay/GeezScriptTokenizer, you can load it from Hugging Face’s Transformers library with just a few lines of code: Don't forget to fix the encoding method.

Downloads last month
5
Safetensors
Model size
125M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Hailay/GeezScriptTokenizer