translation torch==1.8.0

marianmt-zh_cn-th

Training

Training scripts from LalitaDeelert/NLP-ZH_TH-Project. Experiments tracked at cstorm125/marianmt-zh_cn-th.

export WANDB_PROJECT=marianmt-zh_cn-th
python train_model.py --input_fname ../data/v1/Train.csv \\\\\\\\\\\\\\\\
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\t--output_dir ../models/marianmt-zh_cn-th \\\\\\\\\\\\\\\\
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\t--source_lang zh --target_lang th \\\\\\\\\\\\\\\\
\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\t--metric_tokenize th_syllable --fp16 

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
tokenizer = AutoTokenizer.from_pretrained("Lalita/marianmt-zh_cn-th")
model = AutoModelForSeq2SeqLM.from_pretrained("Lalita/marianmt-zh_cn-th").cpu()

src_text = [
    '我爱你',
    '我想吃米饭',
]
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
print([tokenizer.decode(t, skip_special_tokens=True) for t in translated])

> ['ผมรักคุณนะ', 'ฉันอยากกินข้าว']

Requirements

transformers==4.6.0
torch==1.8.0