Update app.py

app.py

@@ -1,23 +1,25 @@
-pip install transformers
-
 from transformers import pipeline
 import gradio as gr
 
-pipe = pipeline(model="MaximilianChen/Casper") 
+model = pipeline(model='MaximilianChen/Casper')
+
 
-def transcribe(audio):
-    text = pipe(audio)["text"]
-    return text
+def transcribe_audio(mic=None, file=None):
+    if mic is not None:
+        audio = mic
+    elif file is not None:
+        audio = file
+    else:
+        return "You must either provide a mic recording or a file"
+    transcription = model(audio)["text"]
+    return transcription
 
-iface = gr.Interface(
-    fn=transcribe, 
+
+gr.Interface(
+    fn=transcribe_audio,
     inputs=[
-        gr.Audio(label="Upload Speech", source="upload", type="numpy"),
-        gr.Audio(label="Record Speech", source="microphone", type="numpy"),
-    ], 
+        gr.Audio(source="microphone", type="filepath", optional=True),
+        gr.Audio(source="upload", type="filepath", optional=True),
+    ],
     outputs="text",
-    title="Casper",
-    description="Realtime demo for Catalan speech recognition using a fine-tuned Whisper small model.",
-)
-
-iface.launch()
+).launch()