ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment
Paper • 2305.14463 • Published
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("tareknaous/readabert-hi")
model = AutoModelForSequenceClassification.from_pretrained("tareknaous/readabert-hi", device_map="auto")Quick Links
Muril-base (muril-base-cased) model fine-tuned on the Hindi portion of the ReadMe++ corpus for sentence-level readability prediction on a scale of 6-level CEFR scale
Github (Dataset and Python Package): https://github.com/tareknaous/readme
- Downloads last month
- 13
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tareknaous/readabert-hi")