chore: Update app.py to support task selection in Arabic Whisper Code-Switching Edition

app.py

@@ -28,11 +28,12 @@ pipe = pipeline(
 )
 
 @spaces.GPU(duration=120)
-def transcribe(inputs):
+def transcribe(inputs, task):
     if inputs is None:
         raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
 
-    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": "transcribe", "language": "arabic"}, return_timestamps=True)["text"]
+    generate_kwargs = {"task": task, "language": "arabic" if task == "transcribe" else "english"}
+    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs=generate_kwargs, return_timestamps=True)["text"]
     return  text
 
 
@@ -71,7 +72,7 @@ def chunks_to_subtitle(chunks):
     return subtitle
 
 @spaces.GPU(duration=120)
-def yt_transcribe(yt_url):
+def yt_transcribe(yt_url, task):
     html_embed_str = _return_yt_html_embed(yt_url)
 
     with tempfile.TemporaryDirectory() as tmpdirname:
@@ -83,7 +84,8 @@ def yt_transcribe(yt_url):
     inputs = ffmpeg_read(inputs, pipe.feature_extractor.sampling_rate)
     inputs = {"array": inputs, "sampling_rate": pipe.feature_extractor.sampling_rate}
 
-    output = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": "transcribe", "language": "arabic"}, return_timestamps=True)
+    generate_kwargs = {"task": task, "language": "arabic" if task == "transcribe" else "english"}
+    output = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs=generate_kwargs, return_timestamps=True)
     subtitle = chunks_to_subtitle(output["chunks"])
 
     return html_embed_str, subtitle
@@ -95,6 +97,7 @@ mf_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
         gr.Audio(sources="microphone", type="filepath"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs="text",
     title="Arabic Whisper Code-Switching Edition: Transcribe Microphone",
@@ -110,6 +113,7 @@ file_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
         gr.Audio(sources="upload", type="filepath", label="Audio file"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs="text",
     title="Arabic Whisper Code-Switching Edition: Transcribe Audio",
@@ -125,6 +129,7 @@ yt_transcribe_demo = gr.Interface(
     fn=yt_transcribe,
     inputs=[
         gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs=["html", "text"],
     title="Arabic Whisper Code-Switching Edition: Transcribe YouTube Video",