🤗 Hindi Sanskrit Model on the Hub

The Hindi-Sanskrit translation model finetuned using contrastive loss on grouped Hindi data 👉 Pretam/hindi_sanskrit

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("Pretam/hindi_sanskrit")
model = AutoModelForSeq2SeqLM.from_pretrained("Pretam/hindi_sanskrit")

article = "इसके लिए साधनों अनुष्ठान तो करना ही चाहिए।"
inputs = tokenizer(article, return_tensors="pt")

translated_tokens = model.generate(
    **inputs, 
    forced_bos_token_id=tokenizer.convert_tokens_to_ids("san_Deva"), # "san_Deva" languages-tag is required for the model to output Sanskrit.
    max_length=30
)

translation = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
print(translation)

🤗 Hindi Kannada Model on the Hub

The Hindi-Kannada translation model. 👉 sanganaka/hin2kan_model

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("sanganaka/hin2kan_model")
model = AutoModelForSeq2SeqLM.from_pretrained("sanganaka/hin2kan_model")

# Input Hindi text
article = "इसके लिए साधनों अनुष्ठान तो करना ही चाहिए।"

# Tokenize input
inputs = tokenizer(article, return_tensors="pt")

# Generate Kannada translation
translated_tokens = model.generate(
    **inputs,
    forced_bos_token_id=tokenizer.convert_tokens_to_ids("kan_Knda")
)

# Decode output
translation = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
print(translation)