Update app.py

app.py

@@ -1,25 +1,14 @@
-from transformers import WhisperProcessor, WhisperForConditionalGeneration
 import gradio as gr
+from transformers import pipeline
 
-# Load model and processor
-processor = WhisperProcessor.from_pretrained("openai/whisper-small")
-model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
+asr_model = pipeline("automatic-speech-recognition", model="openai/whisper-small")
+def transcribe(audio_file):
+    transcription = asr_model(audio_file)
+    return transcription["text"]
 
-def transcribe_audio(audio_file):
-    # Load and process the audio file
-    audio_input, sampling_rate = processor.load_audio(audio_file.name)
-    input_features = processor(audio_input, sampling_rate=sampling_rate, return_tensors="pt").input_features
-
-    # Generate token ids and decode them to text
-    predicted_ids = model.generate(input_features)
-    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
-
-    return transcription[0]
-
-# Set up Gradio interface
 iface = gr.Interface(
-    fn=transcribe_audio,
-    inputs="audio",
+    fn=transcribe,
+    inputs=gr.inputs.Audio(source="microphone", type="filepath"),
     outputs="text"
 )