Update app.py

app.py

@@ -31,17 +31,32 @@ def text_to_speech(text,language):
     lang = language_dict[language]
     gTTS(text,lang,slow=False)
 
+def transcribe_video(URL):
+    video = Youtube(URL)
+    yt = video.streams.get_audio_only()
+    yt.download()
+    text = pipe(yt)["text"]
+    return text
+
+youtube_func = gr.Interface(
+    fn = transcribe_video, 
+    inputs = "text", 
+    outputs = "text",
+    title = "Whisper Small Swedish",,
+    description = "Realtime demo for Swedish speech recognition with translation using a fine-tuned Whisper small model",
+)
 
-
-iface = gr.Interface(
-    fn=transcribe_audio,
+transcribe_func = gr.Interface(
+    fn=transcribe_audio, 
     inputs=[
         gr.Audio(source="microphone", type="filepath", label="Transcribe from Microphone"),
         gr.Dropdown(["English","Spanish","Dutch","French","Italian"], value="English", label="Translate to ")
     ],
     outputs="text",
-    title="Whisper Small Swedish",
-    description="Realtime demo for Swedish speech recognition with translation using a fine-tuned Whisper small model"
-)
+    title=Whisper Small Swedish",,
+    description="Realtime demo for Swedish speech recognition with translation using a fine-tuned Whisper small model",
+
+
+iface = gr.TabbedInterface([transcribe_func, youtube_func], ["Audio to Text","Video transciption"])
 
 iface.launch()