Update app.py

app.py

@@ -4,9 +4,8 @@ subprocess.run(["pip", "install", "datasets"])
 subprocess.run(["pip", "install", "transformers"])
 subprocess.run(["pip", "install", "torch", "torchvision", "torchaudio", "-f", "https://download.pytorch.org/whl/torch_stable.html"])
 
-from transformers import WhisperProcessor, WhisperForConditionalGeneration
-from datasets import load_dataset
 import gradio as gr
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
 
 # Load model and processor
 processor = WhisperProcessor.from_pretrained("openai/whisper-large")
@@ -16,16 +15,21 @@ model.config.forced_decoder_ids = None
 # 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
+    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]
 
+# Custom preprocessing function
+def preprocess_audio(audio_data):
+    # Apply any custom preprocessing to the audio data here if needed
+    return audio_data
+
 # Create Gradio interface
-audio_input = gr.Audio(preprocessing_fn=None)
+audio_input = gr.Audio(preprocess=preprocess_audio)
 gr.Interface(fn=transcribe_audio, inputs=audio_input, outputs="text").launch()