Update app.py

app.py

@@ -1,72 +1,22 @@
 import gradio as gr
-import torch
-from transformers import BertForMaskedLM, BertTokenizer
-import asyncio
-
-# Modell und Tokenizer laden mit force_download=True
-model_name = "bert-base-uncased"
-model = BertForMaskedLM.from_pretrained(model_name, force_download=True)
-tokenizer = BertTokenizer.from_pretrained(model_name, force_download=True)
-
-# Inferenz-Funktion definieren
-def inference(input_text):
-    if "[MASK]" not in input_text:
-        return "Error: The input text must contain the [MASK] token."
-    
-    # Tokenisierung
-    inputs = tokenizer(input_text, return_tensors="pt")
-    mask_token_index = torch.where(inputs["input_ids"] == tokenizer.mask_token_id)[1]
-
-    # Vorhersage
-    with torch.no_grad():
-        outputs = model(**inputs)
-        logits = outputs.logits
+from transformers import pipeline
 
-    # Wahrscheinlichsten Token für [MASK] finden
-    mask_token_logits = logits[0, mask_token_index, :]
-    top_token = torch.topk(mask_token_logits, 1, dim=1).indices[0].tolist()
+# Laden des Modells für Masked Language Modeling
+unmasker = pipeline('fill-mask', model='bert-base-uncased')
 
-    # Vorhersage in den Text einfügen
-    predicted_token = tokenizer.decode(top_token)
-    result_text = input_text.replace("[MASK]", predicted_token, 1)
-    
-    return result_text
+# Gradio Interface
+def masked_language_modeling(text):
+    results = unmasker(text)
+    return results[0]['sequence']
 
-# Gradio Interface definieren
 iface = gr.Interface(
-    fn=inference,
-    inputs="text",
-    outputs="text",
-    examples=[
-        ["The capital of France is [MASK]."],
-        ["The quick brown fox jumps over the [MASK] dog."]
-    ]
+    fn=masked_language_modeling,
+    inputs=gr.Textbox(),
+    outputs=gr.Textbox(),
+    title='BERT Masked Language Modeling',
+    description='Enter a sentence with a [MASK] and see the predictions.'
 )
 
-# Interface starten
-if __name__ == "__main__":
-    # Asynchronen Ereignisloop manuell erstellen und zuweisen
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
-    
-    iface.launch(server_port=7862)
-
-
-from transformers import pipeline
-unmasker = pipeline('fill-mask', model='bert-base-uncased')
-unmasker("Hello I'm a [MASK] model.")
-
-from transformers import BertTokenizer, BertModel
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-model = BertModel.from_pretrained("bert-base-uncased")
-text = "Replace me by any text you'd like."
-encoded_input = tokenizer(text, return_tensors='pt')
-output = model(**encoded_input)
-
-
-from transformers import BertTokenizer, TFBertModel
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-model = TFBertModel.from_pretrained("bert-base-uncased")
-text = "Replace me by any text you'd like."
-encoded_input = tokenizer(text, return_tensors='tf')
-output = model(encoded_input)
+# Starte die Gradio Benutzeroberfläche
+if __name__ == '__main__':
+    iface.launch()