bn-to-en-translation

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

How to use

You can use this model directly with a pipeline:

from transformers import AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("shihab17/bn-to-en-translation")
model = AutoModelForSeq2SeqLM.from_pretrained("shihab17/bn-to-en-translation")

sentence = 'ম্যাচ শেষে পুরস্কার বিতরণের মঞ্চে তামিমের মুখে মোস্তাফিজের প্রশংসা শোনা গেল'

translator = pipeline("translation_en_to_bn", model=model, tokenizer=tokenizer)
output = translator(sentence)
print(output)

bengali-en-to-bn

This model is a fine-tuned version of Helsinki-NLP/opus-mt-bn-en on the kde4 dataset. It achieves the following results on the evaluation set:

• Loss: 1.6885
• Bleu: 50.9475
• Gen Len: 6.7043

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.29.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3