Quickmt Zh En

🚀 quickmt-zh-en Neural Machine Translation Model

quickmt-zh-en is a reasonably fast and reasonably accurate neural machine translation model for translating from zh to en. This model offers an efficient and reliable solution for Chinese-to-English translation tasks.

🚀 Quick Start

📦 Installation

First, install quickmt and download the model:

git clone https://github.com/quickmt/quickmt.git
pip install ./quickmt/

quickmt-model-download quickmt/quickmt-zh-en ./quickmt-zh-en

💻 Usage Examples

🔍 Basic Usage

from quickmt import Translator

# Auto-detects GPU, set to "cpu" to force CPU inference
t = Translator("./quickmt-zh-en/", device="auto")

# Translate - set beam size to 5 for higher quality (but slower speed)
t(["他补充道：“我们现在有 4 个月大没有糖尿病的老鼠，但它们曾经得过该病。”"], beam_size=1)

🔍 Advanced Usage

# Get alternative translations by sampling
# You can pass any cTranslate2 `translate_batch` arguments
t(["他补充道：“我们现在有 4 个月大没有糖尿病的老鼠，但它们曾经得过该病。”"], sampling_temperature=1.2, beam_size=1, sampling_topk=50, sampling_topp=0.9)

✨ Features

• Trained using eole.
• 200M parameter transformer 'big' with 8 encoder layers and 2 decoder layers.
• Separate source and target Sentencepiece tokenizers.
• Exported for fast inference to CTranslate2 format.
• Training data: https://huggingface.co/datasets/quickmt/quickmt-train.zh-en/tree/main.

See the eole model configuration in this repository for further details.

📚 Documentation

The model is in ctranslate2 format, and the tokenizers are sentencepiece. So you can use ctranslate2 directly instead of through quickmt. It is also possible to get this model to work with e.g. LibreTranslate which also uses ctranslate2 and sentencepiece.

🔧 Technical Details

BLEU and CHRF2 calculated with sacrebleu on the Flores200 devtest test set ("zho_Hans"->"eng_Latn"). COMET22 with the comet library and the default model. "Time (s)" is the time in seconds to translate (using ctranslate2) the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32.

quickmt-zh-en is the fastest and highest quality.

📄 License

This project is licensed under the cc-by-4.0 license.