Update app.py

app.py

@@ -4,6 +4,10 @@ import gradio as gr
 asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
 classifier = pipeline("text-classification", "michellejieli/emotion_text_classifier")
 
+def transcribe(audio):
+    text = p(audio)["text"]
+    return text
+    
 def speech_to_text(speech):
     text = asr(speech)["text"]
     return text
@@ -16,20 +20,24 @@ def text_to_sentiment(text):
 demo = gr.Blocks()
 
 with demo:
-   
+
+    microphone = gr.Audio(source="microphone", type="filepath")
     audio_file = gr.Audio(type="filepath")
     text = gr.Textbox()
     label = gr.Label()
 
+    b0 = gr.Button("Classify Sentiment")
     b1 = gr.Button("Recognize Speech")
     b2 = gr.Button("Classify Sentiment")
 
+    b0.click(transcribe, inputs=microphone, outputs=text)
     b1.click(speech_to_text, inputs=audio_file, outputs=text)
     b2.click(text_to_sentiment, inputs=text, outputs=label)
 
     gr.Markdown("""
-    ASR Model: https://huggingface.co/facebook/wav2vec2-base-960h
-    Sentiment: https://huggingface.co/michellejieli/emotion_text_classifier
+    1. ASR Model: https://huggingface.co/facebook/wav2vec2-base-960h
+    2. Sentiment: https://huggingface.co/michellejieli/emotion_text_classifier
+    3. ASR Lesson: https://gradio.app/real-time-speech-recognition/
     """)
 
 demo.launch()