# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("tiagoblima/punctuation-taboa-bert")
model = AutoModelForTokenClassification.from_pretrained("tiagoblima/punctuation-taboa-bert")Quick Links
punctuation-taboa-bert
This model is a fine-tuned version of neuralmind/bert-large-portuguese-cased on the tapaco dataset. It achieves the following results on the evaluation set:
- Loss: 0.0181
- Precision: 0.9850
- Recall: 0.9836
- F1: 0.9843
- Accuracy: 0.9946
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0272 | 1.0 | 17438 | 0.0181 | 0.9850 | 0.9836 | 0.9843 | 0.9946 |
| 0.0234 | 2.0 | 34876 | 0.0196 | 0.9870 | 0.9853 | 0.9862 | 0.9948 |
| 0.0092 | 3.0 | 52314 | 0.0233 | 0.9874 | 0.9853 | 0.9864 | 0.9950 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.13.1
- Downloads last month
- 4
Dataset used to train tiagoblima/punctuation-taboa-bert
Evaluation results
- Precision on tapacoself-reported0.985
- Recall on tapacoself-reported0.984
- F1 on tapacoself-reported0.984
- Accuracy on tapacoself-reported0.995
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="tiagoblima/punctuation-taboa-bert")