Update app.py

app.py

@@ -1,7 +1,25 @@
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+from datasets import load_dataset
 import gradio as gr
 
-def greet(name):
-    return "Hello " + name + "!!"
+# Load model and processor
+processor = WhisperProcessor.from_pretrained("openai/whisper-large")
+model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
+model.config.forced_decoder_ids = None
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+# Function to perform ASR on audio data
+def transcribe_audio(audio_data):
+    # Process audio data using the Whisper processor
+    input_features = processor(audio_data, return_tensors="pt").input_features
+
+    # Generate token ids
+    predicted_ids = model.generate(input_features)
+
+    # Decode token ids to text
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+
+    return transcription[0]
+
+# Create Gradio interface
+audio_input = gr.Audio(preprocessing_fn=None)
+gr.Interface(fn=transcribe_audio, inputs=audio_input, outputs="text").launch()