Cantonese-Chinese-Translation Open-Source Translation Model - Achieve Accurate Translation from Cantonese to Traditional Chinese

Cantonese Chinese Translation

Developed by raptorkwok

A BART-based Cantonese to Traditional Chinese translation model fine-tuned on Cantonese-Traditional Chinese parallel corpus

Machine Translation

Transformers

#Cantonese translation #BART fine-tuning #High BLEU score

Downloads 236

Release Time : 7/10/2023

Model Overview

This model is specifically designed for translating Cantonese text into Traditional Chinese, catering to language conversion needs in Cantonese-speaking regions

Model Features

High-quality translation

Achieves a BLEU score of 62.1085 on the evaluation set, indicating high translation quality

Specialized for Cantonese

Optimized for Cantonese dialect features, capable of handling unique Cantonese expressions

BART-based architecture

Utilizes BART-base Chinese pre-trained model as foundation, with excellent sequence-to-sequence learning capabilities

Model Capabilities

Text translation from Cantonese to Traditional Chinese

Handling unique Cantonese expressions and dialect vocabulary

Use Cases

Language services

Cantonese content localization

Translating Cantonese content into Traditional Chinese for non-Cantonese speakers' understanding

62.1085 BLEU score demonstrates reliable translation quality

Cross-dialect communication

Facilitating text communication between Cantonese and Mandarin speakers

Education

Language learning aid

Assisting students learning Cantonese or Traditional Chinese in understanding correspondences between the two languages

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf	Gen Len
0.3606	0.48	1000	0.2592	60.9844	58.8851	12.8446
0.3059	0.96	2000	0.2291	61.9606	60.1201	12.8621
0.2296	1.44	3000	0.2254	61.9458	60.0434	12.8578
0.2231	1.92	4000	0.2176	61.9617	59.9299	12.8827
0.174	2.39	5000	0.2290	61.9661	59.8844	12.9068
0.171	2.87	6000	0.2258	62.1085	60.1854	12.8755
0.1346	3.35	7000	0.2334	61.4554	59.5055	12.8175
0.1285	3.83	8000	0.2408	61.3332	59.3276	12.8412
0.1061	4.31	9000	0.2530	61.6505	59.614	12.8566

Property	Details
Model Type	Fine - tuned version of fnlp/bart - base - chinese
Training Data	raptorkwok/cantonese - traditional - chinese - parallel - corpus

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Cantonese Chinese Translation

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 Cantonese-Chinese Translation

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions