Text2Text Generation
Safetensors
Azerbaijani
t5
spell
correction
azerbaijani
vrashad commited on
Commit
4b7e3b5
·
verified ·
1 Parent(s): b866085

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -8
README.md CHANGED
@@ -23,7 +23,6 @@ This repository contains an Azerbaijani spell correction model based on `google/
23
  - [Imitating Real Spelling Errors](#imitating-real-spelling-errors)
24
  - [Keyboard Layout Considerations](#keyboard-layout-considerations)
25
  - [Typical Substitutions](#typical-substitutions)
26
- - [Model Training](#model-training)
27
  - [Usage](#usage)
28
  - [License](#license)
29
  - [Contact](#сontact)
@@ -86,13 +85,6 @@ Several typical substitutions were included in the dataset to reflect common err
86
 
87
  These substitutions represent phonetic similarities and common mistakes made by speakers when writing Azerbaijani text, especially when using Latin characters.
88
 
89
- ## Model Training
90
-
91
- The model was fine-tuned using the Hugging Face Transformers library. Key points in the training process include:
92
-
93
- - **Model Architecture:** `google/mt5-small` was chosen for its multilingual support and capability to handle Azerbaijani characters.
94
- - **Training Objective:** The model was trained to map incorrect sentences to their correct versions.
95
- - **Evaluation:** The performance was evaluated using metrics like BLEU and ROUGE to ensure the quality of corrections.
96
 
97
  ## Usage
98
 
 
23
  - [Imitating Real Spelling Errors](#imitating-real-spelling-errors)
24
  - [Keyboard Layout Considerations](#keyboard-layout-considerations)
25
  - [Typical Substitutions](#typical-substitutions)
 
26
  - [Usage](#usage)
27
  - [License](#license)
28
  - [Contact](#сontact)
 
85
 
86
  These substitutions represent phonetic similarities and common mistakes made by speakers when writing Azerbaijani text, especially when using Latin characters.
87
 
 
 
 
 
 
 
 
88
 
89
  ## Usage
90