Update app.py

app.py

@@ -40,27 +40,53 @@ description = """
 Demo for cascaded speech-to-speech translation (STST), mapping from source speech in Multilanguage to target speech in Chinese(mandarin). Demo uses OpenAI's [Whisper arge-v2](https://huggingface.co/openai/whisper-large-v2) model for speech translation, and a suno/bark[bark-small](https://huggingface.co/suno/bark) model for text-to-speech:
 ![Cascaded STST](https://huggingface.co/datasets/huggingface-course/audio-course-images/resolve/main/s2st_cascaded.png "Diagram of cascaded speech to speech translation")
 """
+examples = [
+    ["/mama (1).mp3", None],
+    ["/mama (2).mp3", None],
+    ["/mama (3).mp3", None],
+    ["/mama (4).mp3", None],
+    ["/mama (5).mp3", None],
+    ["/mama (6).mp3", None],
+    ["/mama (7).mp3", None],
+    ["/mama (8).mp3", None],
+]
 import gradio as gr
 demo = gr.Blocks()
 
-mic_translate = gr.Interface(
-    fn=speech_to_speech_translation_fix,
-    inputs=gr.Audio(source="microphone", type="filepath"),
-    outputs=gr.Audio(label="Generated Speech", type="numpy"),
+Muti_translate=gr.Interface(
+    fn=peech_to_speech_translation_fix,
+    inputs=[
+        gr.Audio(label="Upload Speech", source="upload", type="numpy"),
+        gr.Audio(label="Record Speech", source="microphone", type="numpy"),
+    ],
+    outputs=[
+        outputs=gr.Audio(label="Generated Speech", type="numpy"),
+    ],
     title=title,
     description=description,
+    article=article,
+    examples=examples,
 )
 
-file_translate = gr.Interface(
-    fn=speech_to_speech_translation_fix,
-    inputs=gr.Audio(source="upload", type="filepath"),
-    outputs=gr.Audio(label="Generated Speech", type="numpy"),
-    examples=[["./example.wav"]],
-    title=title,
-    description=description,
-)
+# mic_translate = gr.Interface(
+#     fn=speech_to_speech_translation_fix,
+#     inputs=gr.Audio(source="microphone", type="filepath"),
+#     outputs=gr.Audio(label="Generated Speech", type="numpy"),
+#     title=title,
+#     description=description,
+# )
+
+# file_translate = gr.Interface(
+#     fn=speech_to_speech_translation_fix,
+#     inputs=gr.Audio(source="upload", type="filepath"),
+#     outputs=gr.Audio(label="Generated Speech", type="numpy"),
+#      examples=examples,
+#     title=title,
+#     description=description,
+# )
 
 with demo:
-    gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
+    # gr.TabbedInterface([mic_translate, file_translate], ["Microphone", "Audio File"])
+    gr.TabbedInterface([Muti_translate], ["Record or upload your speech"])
 
 demo.launch(share=True)