KES commited on
Commit
940b0ec
·
1 Parent(s): 4f9a576

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -0
README.md CHANGED
@@ -1,3 +1,33 @@
1
  ---
 
 
 
 
 
 
2
  license: apache-2.0
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+
4
+ - Translation
5
+
6
+ - text2text-generation
7
+
8
  license: apache-2.0
9
+
10
  ---
11
+
12
+ # Trinidad English Creole to English Translator
13
+ This model utilises T5-base pre-trained model. It was fine tuned using a custom dataset for translation of Trinidad English Creole to English. This model will be updated periodically as more data is compiled. For more on the Caribbean English Creole checkout the library [Caribe](https://pypi.org/project/Caribe/).
14
+
15
+
16
+
17
+ ___
18
+
19
+ # Usage with Transformers
20
+ ```python
21
+ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
22
+ tokenizer = AutoTokenizer.from_pretrained("KES/TEC-English")
23
+
24
+ model = AutoModelForSeq2SeqLM.from_pretrained("KES/TEC-English")
25
+ text = "Dem men doh kno wat dey doing wid d money"
26
+ inputs = tokenizer("tec:"+text, truncation=True, return_tensors='pt')
27
+
28
+ output = model.generate(inputs['input_ids'], num_beams=4, max_length=512, early_stopping=True)
29
+ correction=tokenizer.batch_decode(output, skip_special_tokens=True)
30
+ print("".join(correction)) #Correction: These men do not know what they are doing with the money.
31
+ ```
32
+ ___
33
+