Create app.py

app.py

@@ -0,0 +1,20 @@
+import gradio as gr
+from transformers import pipeline
+import numpy as np
+import soundfile as sf
+
+
+pipe1 = pipeline("automatic-speech-recognition", model="openai/whisper-base")
+
+def transcribe_audio(audio):
+    audio_data, _ = sf.read(audio)  # Load audio file
+    audio_array = np.array(audio_data)  # Convert to numpy array
+    
+    transcription = pipe1(audio_array)
+    transcription_text = transcription['text']
+    
+    return transcription_text
+
+# Gradio interface
+demo = gr.Interface(fn=transcribe_audio, inputs=gr.Audio(source="microphone", type="filepath"), outputs="text")
+demo.launch(share=True)