Update app.py

app.py

@@ -1,35 +1,43 @@
 from transformers import pipeline
 
-# Load the ASR pipeline
-asr = pipeline(task="automatic-speech-recognition", model="facebook/wav2vec2-base-960h")
+asr = pipeline(task="automatic-speech-recognition",
+              model="distil-whisper/distil-small.en")
 
 import gradio as gr
+demo = gr.Blocks()
 
 def transcribe_speech(filepath):
     if filepath is None:
         gr.Warning("No Audio found, please retry")
         return ""
 
-    # Perform speech recognition using the Hugging Face ASR pipeline
     output = asr(filepath)
-    return output[0]['transcription']
+    return output["text"]
 
 mic_transcribe = gr.Interface(
     fn = transcribe_speech,
-    inputs = gr.Audio(sources="microphone", type="file"), 
-    outputs=gr.Textbox(label="Transcription", lines=3),
+    inputs = gr.Audio(sources="microphone",
+                     type="filepath"), 
+    outputs=gr.Textbox(label="Transcription", 
+                      lines=3),
     allow_flagging="never"
 )
 
 file_transcribe = gr.Interface(
     fn = transcribe_speech,
-    inputs = gr.Audio(sources="upload", type="file"), 
-    outputs=gr.Textbox(label="Transcription", lines=3),
+    inputs = gr.Audio(sources="upload",
+                     type="filepath"), 
+    outputs=gr.Textbox(label="Transcription", 
+                      lines=3),
     allow_flagging="never"
 )
 
-with gr.Block():
+with demo:
     gr.TabbedInterface(
-        [mic_transcribe, file_transcribe], 
-        ["Transcribe Microphone", "Transcribe Audio File"], 
-    ).launch(debug=True)
+        [mic_transcribe, 
+        file_transcribe], 
+        ["Transcribe Microphone", 
+        "Transcribe Audio File"], 
+    )
+
+demo.launch(debug=True)