Downloads · 30 days
10
1% of all-time downloads
t5_interpreter
inkoziev/t5_interpreter
t5_interpreter is a machine learning model from inkoziev. 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 lgpl-3.0.
A rut5-based model for incomplete utterance restoration, spellchecking and text normalization for dialogue utterances.
All-time downloads
1K
Public
Repo size
777 MB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin259 MB · 100%
At a glance
- Library
- transformers
- License
- lgpl-3.0
- Model type
- t5
- Access
- Public
- Created
- Nov 8, 2022
- Updated
- Nov 28, 2022
- SHA
- 72efb9a5
Model card
From the Hugging Face model README
t5_interpreter
A rut5-based model for incomplete utterance restoration, spellchecking and text normalization for dialogue utterances.
Read more about the task here.
Usage example
import torch
from transformers import T5ForConditionalGeneration, T5Tokenizer
model_name = 'inkoziev/t5_interpreter'
tokenizer = T5Tokenizer.from_pretrained(model_name,)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = T5ForConditionalGeneration.from_pretrained(model_name)
model.eval()
t5_input = '- Тебя как зовут?\n- Мальвина #'
input_ids = tokenizer(t5_input, return_tensors='pt').input_ids
out_ids = model.generate(input_ids=input_ids, max_length=40, eos_token_id=tokenizer.eos_token_id, early_stopping=True)
t5_output = tokenizer.decode(out_ids[0][1:])
print(t5_output)
- Library
- transformers
- Type
- t5
- License
- lgpl-3.0
- Created
- Nov 8, 2022
- Updated
- Nov 28, 2022