Update app.py

app.py

@@ -1,11 +1,16 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Load Model
+model_directory = 'paulpall/GEC_Estonian_OPUS-MT'
+tokenizer = AutoTokenizer.from_pretrained(model_directory)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_directory)
 
 def respond(
     message,
@@ -25,19 +30,14 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Generate corrected sentence
+    input_ids = tokenizer.encode(message, padding='max_length', truncation=True, max_length=128, return_tensors='pt')
+    output_ids = model.generate(input_ids=input_ids.to(model.device))
+    output_sentence = tokenizer.decode(output_ids[0], skip_special_tokens=True).replace(r"▁",r" ")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    response = output_sentence
 
-        response += token
-        yield response
+    yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -58,6 +58,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()