Downloads · 30 days
4
10% of all-time downloads
spelling-correction-english-base-location-unique-2
grantslewis/spelling-correction-english-base-location-unique-2
spelling-correction-english-base-location-unique-2 is a machine learning model from grantslewis. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
42
Public
Repo size
1.7 GB
Likes
5
Public
Repo makeup
Click a slice to open those files.
.bin558 MB · 99%
At a glance
- Library
- transformers
- License
- mit
- Model type
- bart
- Access
- Public
- Created
- Oct 7, 2022
- Updated
- Oct 7, 2022
- SHA
- 35fd3bd4
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
spelling-correction-english-base-location-unique-2
This model is a fine-tuned version of oliverguhr/spelling-correction-english-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9149
- Cer: 0.1747
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: 70
- eval_batch_size: 70
- 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 | Cer |
|---|---|---|---|---|
| No log | 1.0 | 470 | 1.0012 | 0.1850 |
| 1.2217 | 2.0 | 940 | 0.9337 | 0.1747 |
| 1.0032 | 3.0 | 1410 | 0.9149 | 0.1747 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1
- Library
- transformers
- Type
- bart
- License
- mit
- Created
- Oct 7, 2022
- Updated
- Oct 7, 2022