Update app.py

app.py

@@ -27,9 +27,23 @@ import numpy as np
 import json
 from datetime import timedelta
 
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+
 __FILES = set()
 wispher_models = list(whisper._MODELS.keys())
 
+def correct_grammar(input_text,num_return_sequences=num_return_sequences):
+    torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
+    tokenizer = T5Tokenizer.from_pretrained('deep-learning-analytics/GrammarCorrector')
+    model = T5ForConditionalGeneration.from_pretrained('deep-learning-analytics/GrammarCorrector').to(torch_device)
+    batch = tokenizer([input_text],truncation=True,padding='max_length',max_length=len(input_text), return_tensors="pt").to(torch_device)
+    results = model.generate(**batch,max_length=len(input_text),num_beams=2, num_return_sequences=num_return_sequences, temperature=1.5)
+    generated_sequences = []
+    for generated_sequence_idx, generated_sequence in enumerate(results):
+        text = tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True, skip_special_tokens=True)
+        generated_sequences.append(text)
+    return "".join(generated_sequences)
+
 def CreateFile(filename):
     __FILES.add(filename)
     return filename