Update app.py

app.py

@@ -37,7 +37,7 @@ def format_timestamp(seconds: float, always_include_hours: bool = False, decimal
 
 
 def transcribe(file, task, return_timestamps):
-    outputs = pipe(file, batch_size=BATCH_SIZE, return_timestamps=return_timestamps)
+    outputs = pipe(file, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=return_timestamps)
     text = outputs["text"]
     if return_timestamps:
         timestamps = outputs["chunks"]
@@ -49,10 +49,32 @@ def transcribe(file, task, return_timestamps):
     return text
 
 
+demo = gr.Blocks()
+
+mic_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
+        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
+        gr.inputs.Checkbox(default=False, label="Return timestamps"),
+    ],
+    outputs="text",
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Demo: Transcribe Audio",
+    description=(
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
+        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
+        " of arbitrary length."
+    ),
+    allow_flagging="never",
+)
+
 file_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.inputs.Audio(source="upload", label="Audio file", type="filepath"),
+        gr.inputs.Audio(source="upload", optional=True, label="Audio file", type="filepath"),
+        gr.inputs.Radio(["transcribe"], label="Task", default="transcribe"),
         gr.inputs.Checkbox(default=False, label="Return timestamps"),
     ],
     outputs="text",
@@ -64,6 +86,8 @@ file_transcribe = gr.Interface(
         f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
         " of arbitrary length."
     ),
+    
+    cache_examples=True,
     allow_flagging="never",
 )