ne-bert

# First, install the library:
# pip install -U transformers

from transformers import AutoTokenizer, AutoModelForMaskedLM
import torch

# Load NE-BERT (No remote code needed for transformers >= 4.48)
model_name = "MWirelabs/ne-bert"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForMaskedLM.from_pretrained(model_name)

# Example: Nagamese Creole (ISO: nag)
text = "Moi bhat <mask>." # "I [eat] rice"
inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    logits = model(**inputs).logits

# Retrieve top prediction
mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(as_tuple=True)[0]
predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)
print(tokenizer.decode(predicted_token_id))
# Output: "khai" (eat)