English2Hinglish-Flan-T5-Base

This is a finetuned model of google/flan-t5-base with rvv-karma/English-Hinglish-TOP dataset.

Usage

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_name = "rvv-karma/English2Hinglish-Flan-T5-Base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

input_text = "What are you doing?"
input_ids = tokenizer(input_text, return_tensors="pt")
output_ids = model.generate(**input_ids)
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)

print(output_text)

Fine-tuning script

Google Colaboratory Notebook

References

DataCamp