|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- agentlans/high-quality-english-sentences |
|
language: |
|
- en |
|
base_model: |
|
- google-t5/t5-base |
|
library_name: transformers |
|
tags: |
|
- Safetensors |
|
--- |
|
|
|
This model is for typos in texts and it outputs corrected texts. |
|
|
|
Example: |
|
|
|
Text with Typos: **Whathvhr wh call owr carhaivhrs - doctors, nwrsh practitionhrs, clinicians, - wh nhhd thhm not only to carh, wh nhhd thhm to uh aulh to providh thh riaht valwh.** |
|
|
|
Corrected Text: **Whatever we call our caregivers - doctors, nurse practitioners, clinicians, - we need them not only to care, we need them to be able to provide the right value.** |
|
|
|
|
|
Example Usage: |
|
```py |
|
#Load the model and tokenizer |
|
text = "" #Text with typos here! |
|
inputs = tokenizer(cipher_text, return_tensors="pt", padding=True, truncation=True, max_length=256).to(device) |
|
outputs = model.generate(inputs["input_ids"], max_length=256) |
|
corrected_text = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
``` |
