111

app.py

@@ -1,17 +1,24 @@
 import gradio as gr
+from transformers import pipeline
+import time
 
-def process_image(image):
-    # Placeholder function to process the image
-    # For now, it just returns the image as is
-    return image
+pipe = pipeline("automatic-speech-recognition")
 
-# Create a Gradio interface
-iface = gr.Interface(
-    fn=process_image,           # Function to process the image
-    inputs=gr.Image(source="webcam", tool="editor"),  # Capture image from webcam
-    outputs="image",            # Output type is an image
-    live=True                   # Enable live webcam feed
-)
+def transcribe(audio, state=""):
+    print(audio)
+    time.sleep(2)
+    text = pipe(audio)["text"]
+    state += text + " "
+    return state, state
 
-# Launch the interface
-iface.launch()
+
+with gr.Blocks() as demo:
+  state = gr.State(value="")
+  with gr.Row():
+      with gr.Column():
+        audio = gr.Audio(source="microphone", type="filepath") 
+      with gr.Column():
+        textbox = gr.Textbox()
+  audio.stream(fn=transcribe, inputs=[audio, state], outputs=[textbox, state])
+
+demo.launch(debug=True)