Arabic_poem_meter_3 /
Yah216's picture
language: ar
  - text: قفا نبك من ذِكرى حبيب ومنزلِ  بسِقطِ اللِّوى بينَ الدَّخول فحَوْملِ
  - text: سَلو قَلبي غَداةَ سَلا وَثابا لَعَلَّ عَلى الجَمالِ لَهُ عِتابا
co2_eq_emissions: 404.66986451902227

Model Trained Using AutoTrain

  • Problem type: Multi-class Classification
  • CO2 Emissions (in grams): 404.66986451902227


We used the APCD dataset cited hereafter for pretraining the model. The dataset has been cleaned and only the main text and the meter columns were kept:

  author =       {Yousef, Waleed A. and Ibrahime, Omar M. and Madbouly, Taha M. and Mahmoud,
                  Moustafa A.},
  title =        {Learning Meters of Arabic and English Poems With Recurrent Neural Networks: a Step
                  Forward for Language Understanding and Synthesis},
  journal =      {arXiv preprint arXiv:1905.05700},
  year =         2019,
  url =          {}

Validation Metrics

  • Loss: 0.21315555274486542
  • Accuracy: 0.9493554089595999
  • Macro F1: 0.7537353091512587


You can use cURL to access this model:

$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "قفا نبك من ذِكرى حبيب ومنزلِ  بسِقطِ اللِّوى بينَ الدَّخول فحَوْملِ"}'

Or Python API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("Yah216/Arabic_poem_meter_3", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("Yah216/Arabic_poem_meter_3", use_auth_token=True)

inputs = tokenizer("قفا نبك من ذِكرى حبيب ومنزلِ  بسِقطِ اللِّوى بينَ الدَّخول فحَوْملِ", return_tensors="pt")

outputs = model(**inputs)