Instructions to use LocaleNLP/localenlp-eng-wol-0.03 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LocaleNLP/localenlp-eng-wol-0.03 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="LocaleNLP/localenlp-eng-wol-0.03")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("LocaleNLP/localenlp-eng-wol-0.03") model = AutoModelForSeq2SeqLM.from_pretrained("LocaleNLP/localenlp-eng-wol-0.03") - Notebooks
- Google Colab
- Kaggle
English β Hausa Translation Model (localenlp-eng-wol-0.01)
This model is a fine-tuned version of Helsinki-NLP/opus-mt-mul-en for translating **English (eng) to Wolof (wol) **. It was trained on 84,000 parallel sentence pairs and achieves strong performance on held-out test sets.
Developed and maintained by LocaleNLP β advancing African language technologies.
Metrics
BLEU Score: 76.12
chrF Score: 82.22
Limitations and Bias
Data Limitations: Training data of 84k sentences may not cover all Wolof dialects and domains
Bias Potential: May reflect biases present in the training data
Format Sensitivity: Performance may vary with input formatting and punctuation
Domain Adaptation: Best performance on text similar to training data
Model Card Authors
[Mgolo/LocaleNLP]
Framework Versions
Transformers 4.30.0
PyTorch 2.0.0+
Tokenizers 0.13.3
- Downloads last month
- -