Update app.py

app.py

@@ -1,15 +1,4 @@
 import subprocess
-
-
-subprocess.run(["python", "-m", "pip", "install", "--upgrade", "pip"])
-subprocess.run(["pip", "install", "gradio", "--upgrade"])
-subprocess.run(["pip", "install", "soundfile"])
-subprocess.run(["pip", "install", "numpy"])
-subprocess.run(["pip", "install", "pydub"])
-subprocess.run(["pip", "install", "openai"])
-
-import subprocess
-
 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"])
@@ -22,21 +11,19 @@ processor = WhisperProcessor.from_pretrained("openai/whisper-large")
 model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
 model.config.forced_decoder_ids = None
 
-# Custom preprocessing function
-def preprocess_audio(audio_data):
-    # Apply any custom preprocessing to the audio data here if needed
-    return processor(audio_data, return_tensors="pt").input_features
-
 # Function to perform ASR on audio data
-def transcribe_audio(input_features):
+def transcribe_audio(audio_data):
+    # Apply custom preprocessing to the audio data if needed
+    processed_input = processor(audio_data, return_tensors="pt").input_features
+
     # Generate token ids
-    predicted_ids = model.generate(input_features)
-    
+    predicted_ids = model.generate(processed_input)
+
     # 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(preprocess=preprocess_audio)
-gr.Interface(fn=transcribe_audio, inputs=audio_input, outputs="text").launch()
+audio_input = gr.Audio()
+gr.Interface(fn=transcribe_audio, inputs=audio_input, outputs="text").launch()