updating gradio interface

app.py

@@ -71,7 +71,7 @@ def transcribe_and_classify_speech(audio):
     native_accent_output = native_accent_classifier(audio)
   except Exception as e:
     print(f"An error occurred with Jzuluaga/accent-id-commonaccent_ecapa: {e}")
-    native_accent_output = [{'accent': 'Unknown-please upload single channel audio'}, {'score': .0}]
+    native_accent_output = [{'accent': e}, {'score': .0}]
 
   try:
     esl_accent_output = esl_accent_classifier(audio)
@@ -88,36 +88,38 @@ def transcribe_and_classify_speech(audio):
   ]
   return output
 
+## Set up gradio app
 demo = gr.Blocks()
 
-examples = [['chinese-american.wav'], ['mexican.wav'], ['vietnamese.wav'], ['indian.wav'], ['nigerian.wav']]
-
-mic_transcribe = gr.Interface(
-    fn=transcribe_and_classify_speech,
-    inputs=gr.Audio(sources="microphone", type="filepath"),
-    outputs=gr.components.Textbox(),
-    examples=examples,
-)
-
-file_transcribe = gr.Interface(
-    fn=transcribe_and_classify_speech,
-    inputs=gr.Audio(sources="upload", type="filepath"),
-    outputs=gr.components.Textbox(),
-    examples=examples,
-)
-
-# Launch gradio app demo
-with demo:
-  gr.TabbedInterface(
+examples = [['chinese-american.wav'], ['mexican.wav'], ['vietnamese.wav'], ['indian.wav'], ['nigerian.wav'], ['irish.wav']]
+
+# Create a function to generate a vertically stacked interface
+def create_transcription_interface(source):
+    with gr.Blocks() as interface:
+        gr.Markdown("""
+        Input: Use microphone, upload .wav file, or choose an example below 
+        Output will include results from the following models: 
+          - Transcription from OpenAI's Whisper [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en)
+          - Phonemic transcription trained on native English speakers [vitouphy/wav2vec2-xls-r-300m-timit-phoneme](https://huggingface.co/vitouphy/wav2vec2-xls-r-300m-timit-phoneme)
+          - Phonemic transcription trained on speakers of English as a second language [mrrubino/wav2vec2-large-xlsr-53-l2-arctic-phoneme](https://huggingface.co/mrrubino/wav2vec2-large-xlsr-53-l2-arctic-phoneme)
+          - Accent classification trained on native English speakers [Jzuluaga/accent-id-commonaccent_ecapa](https://huggingface.co/Jzuluaga/accent-id-commonaccent_ecapa)
+          - Accent classification trained on speakers of English as a second language [kaysrubio/accent-id-distilhubert-finetuned-l2-arctic2](https://huggingface.co/kaysrubio/accent-id-distilhubert-finetuned-l2-arctic2)
+        """)
+        with gr.Column():
+            audio_input = gr.Audio(sources=source, type="filepath", label="Upload Audio")
+            output = gr.JSON(label="Results")
+        audio_input.change(fn=transcribe_and_classify_speech, inputs=audio_input, outputs=output)
+        gr.Examples(examples=examples, inputs=[audio_input])
+    return interface
+
+# Create two interfaces (one for mic, one for file upload)
+mic_transcribe = create_transcription_interface("microphone")
+file_transcribe = create_transcription_interface("upload")
+
+demo = gr.TabbedInterface(
     [mic_transcribe, file_transcribe],
-    ["Transcribe Microphone", "Transcribe Audio File"],
-  )
-
-demo.launch(debug=True)
-
-
-#def greet(name):
-#    return "Hello " + name + "!!"
+    ["Microphone Input", "Upload .wav file"],
+    title="Speech Transcription, Phonemic Transcription, and Accent Classification",
+)
 
-#demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-#demo.launch()
+demo.launch(debug=True)