Downloads · 30 days
31
1% of all-time downloads
distilbert-base-multi-cased-finetuned-typo-detection
mrm8488/distilbert-base-multi-cased-finetuned-typo-detection
distilbert-base-multi-cased-finetuned-typo-detection is a token classification model from mrm8488. Use it when you need labels on individual words, such as names. It is set up for transformers.
distilbert-base-multilingual-cased fine-tuned on GitHub Typo Corpus for typo detection (using NER style)
All-time downloads
2.9K
Public
Parameters
135M
1.1 GB on disk
Likes
6
Public
Repo makeup
Click a slice to open those files.
.bin539 MB · 50%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Mar 26, 2023
- SHA
- 10caef70
Model card
From the Hugging Face model README
DISTILBERT 🌎 + Typo Detection ✍❌✍✔
distilbert-base-multilingual-cased fine-tuned on GitHub Typo Corpus for typo detection (using NER style)
Details of the downstream task (Typo detection as NER)
-
Dataset: GitHub Typo Corpus 📚 for 15 languages
-
Fine-tune script on NER dataset provided by Huggingface 🏋️♂️
Metrics on test set 📋
| Metric | # score |
|---|---|
| F1 | 93.51 |
| Precision | 96.08 |
| Recall | 91.06 |
Model in action 🔨
Fast usage with pipelines 🧪
from transformers import pipeline
typo_checker = pipeline(
"ner",
model="mrm8488/distilbert-base-multi-cased-finetuned-typo-detection",
tokenizer="mrm8488/distilbert-base-multi-cased-finetuned-typo-detection"
)
result = typo_checker("Adddd validation midelware")
result[1:-1]
# Output:
[{'entity': 'ok', 'score': 0.7128152847290039, 'word': 'add'},
{'entity': 'typo', 'score': 0.5388424396514893, 'word': '##dd'},
{'entity': 'ok', 'score': 0.94792640209198, 'word': 'validation'},
{'entity': 'typo', 'score': 0.5839331746101379, 'word': 'mid'},
{'entity': 'ok', 'score': 0.5195121765136719, 'word': '##el'},
{'entity': 'ok', 'score': 0.7222476601600647, 'word': '##ware'}]
It works🎉! We typed wrong Add and middleware
Created by Manuel Romero/@mrm8488
Made with <span style="color: #e25555;">♥</span> in Spain
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- Languages
- multilingual, en, zh, ja, ru, fr
- Created
- Mar 2, 2022
- Updated
- Mar 26, 2023