metadata

language:
  - es
  - qu
tags:
  - quechua
  - translation
  - spanish
license: apache-2.0

t5-small-finetuned-spanish-to-quechua

This model is a finetuned version of the t5-small.

Model description

Intended uses & limitations

How to use

You can import this model as follows:

>>> from transformers import AutoModelForSeq2SeqLM
>>> from transformers import AutoTokenizer
>>> model_name = 'hackathon-pln-es/t5-small-finetuned-spanish-to-quechua'
>>> model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
>>> tokenizer = AutoTokenizer.from_pretrained(model_name)

To translate you can do:

>>> sentence = "Entonces dijo"
>>> input = tokenizer(text, return_tensors="pt")
>>> output = model.generate(input["input_ids"], max_length=40, num_beams=4, early_stopping=True)
>>> print('Original Sentence: {} \nTranslated sentence: {}'.format(sentence, tokenizer.decode(output[0])))

Limitations and bias

Training data

Evaluation results

We obtained the following metrics during the training process:

eval_bleu = 2.9691 eval_loss = 1.2064628601074219