Update app.py

app.py

@@ -1,51 +1,28 @@
-from gradio import Interface
-import json
-from tensorflow.keras.models import load_model  # Assuming TensorFlow backend
-#from keras.preprocessing.text import Tokenizer  # Assuming Keras Tokenizer
+import gradio as gr
+from huggingface_hub import from_pretrained_keras
+from transformers import AutoTokenizer
 
-# Model and tokenizer loading paths (replace with your actual paths)
-model_path = "Bajiyo/mal_en_transliteration"
-source_tokenizer_config_path = "https://huggingface.co/Bajiyo/Malayalam_transliteration/blob/main/source_tokenizer_config.json"
-target_tokenizer_config_path = "https://huggingface.co/Bajiyo/Malayalam_transliteration/blob/main/target_tokenizer_config.json"
+# Load the model from Hugging Face
+model = from_pretrained_keras("Bajiyo/Malayalam_transliteration")
 
-# Load the model
-model = load_model(model_path)
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Bajiyo/Malayalam_transliteration")
 
-# Load tokenizers
-with open(source_tokenizer_config_path, "r") as f:
-    source_tokenizer = Tokenizer.from_config(json.load(f))
+# Define a function to make predictions
+def predict(text):
+    # Tokenize the input text
+    inputs = tokenizer(text, return_tensors="tf", padding=True, truncation=True)
 
-with open(target_tokenizer_config_path, "r") as f:
-    target_tokenizer = Tokenizer.from_config(json.load(f))
+    # Make predictions using the model
+    outputs = model.predict(inputs)
 
+    # Decode the predicted tokens
+    predicted_text = tokenizer.decode(outputs.logits[0], skip_special_tokens=True)
 
-def transliterate(malayalam_name):
-    # Preprocess input (e.g., handle punctuation, special characters)
-    processed_name = preprocess_malayalam_name(malayalam_name)  # Implement your preprocessing logic
-
-    # Tokenize the input
-    sequence = source_tokenizer.texts_to_sequences([processed_name])[0]
-
-    # Pad the sequence
-    padded_sequence = pad_sequences([sequence], maxlen=MAX_SEQ_LENGTH, padding="post")
-
-    # Make prediction
-    prediction = model.predict(padded_sequence)[0]
-
-    # Detokenize the predicted sequence
-    transliterated_name = target_tokenizer.sequences_to_texts([np.argmax(prediction)])[0]
-
-    return transliterated_name
-
-# Define the maximum sequence length your model was trained on
-MAX_SEQ_LENGTH = 49  # Replace with the actual value
-
-interface = Interface(
-    fn=transliterate,
-    inputs="text",
-    outputs="text",
-    title="Malayalam to English Transliteration",
-    description="Enter a Malayalam name and get the transliterated English version.",
-)
+    return predicted_text
 
+# Create a Gradio interface
+inputs = gr.inputs.Textbox(label="Enter Malayalam Text")
+outputs = gr.outputs.Textbox(label="Transliteration to English")
+interface = gr.Interface(predict, inputs, outputs, title="Malayalam to English Transliteration")
 interface.launch()