Update app.py

app.py

@@ -26,25 +26,29 @@ feat_ext = WhisperFeatureExtractor.from_pretrained("rohitp1/kkkh_whisper_small_d
 
 p = pipeline('automatic-speech-recognition', model=model, tokenizer=tokenizer, feature_extractor=feat_ext)
 
-def transcribe(audio, state=""):
+def transcribe(mic_input, upl_input):
+    if mic_input:
+        audio = mic_input
+    else:
+        audio = upl_input
     time.sleep(3)
     text = p(audio)["text"]
-    state = text + " "
-    return state, state
+    # state = text + " "
+    return text
 
 
 
-gr.Interface(
-    fn=transcribe, 
-    inputs=[
-        gr.inputs.Audio(source="microphone", type="filepath"),
-        'state'
-    ],
-    outputs=[
-        "textbox",
-        "state"
-    ],
-    live=False).launch()
+# gr.Interface(
+#     fn=transcribe, 
+#     inputs=[
+#         gr.inputs.Audio(source="microphone", type="filepath"),
+#         'state'
+#     ],
+#     outputs=[
+#         "textbox",
+#         "state"
+#     ],
+#     live=False).launch()
 
 
 # demo = gr.load(
@@ -55,4 +59,64 @@ gr.Interface(
 #     api_key="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"
 # )
 
-# demo.launch()
+# demo.launch()
+
+def clear_inputs_and_outputs():
+    return [None, None, None]
+
+# Main function
+if __name__ == "__main__":
+    demo = gr.Blocks()
+
+    with demo:
+        gr.Markdown(
+            """
+            <center><h1>English speaker accent recognition using Transfer Learning</h1></center> \
+            This space is a demo of an English (precisely UK & Ireland) accent classification model using Keras.<br> \
+    In this space, you can record your voice or upload a wav file and the model will predict the English accent spoken in the audio<br><br>
+            """
+        )
+        with gr.Row():
+            ## Input
+            with gr.Column():
+                mic_input = gr.Audio(source="microphone", label="Record your own voice")
+                upl_input = gr.Audio(
+                    source="upload", type="filepath", label="Upload a wav file"
+                )
+
+                with gr.Row():
+                    clr_btn = gr.Button(value="Clear", variant="secondary")
+                    prd_btn = gr.Button(value="Predict")
+
+            # Outputs
+            with gr.Column():
+                lbl_output = gr.Label(label="Top Predictions")
+                # with gr.Group():
+                #     gr.Markdown("<center>Prediction per time slot</center>")
+                #     plt_output = gr.Plot(
+                #         label="Prediction per time slot", show_label=False
+                #     )
+
+        # Credits
+        with gr.Row():
+            gr.Markdown(
+                """
+                <h4>Credits</h4>
+                Author: <a href="https://twitter.com/fadibadine"> Fadi Badine</a>.<br>
+                Based on the following Keras example <a href="https://keras.io/examples/audio/uk_ireland_accent_recognition"> English speaker accent recognition using Transfer Learning</a> by Fadi Badine<br>
+                Check out the model <a href="https://huggingface.co/keras-io/english-speaker-accent-recognition-using-transfer-learning">here</a>
+                """
+            )
+
+        clr_btn.click(
+            fn=clear_inputs_and_outputs,
+            inputs=[],
+            outputs=[mic_input, upl_input, lbl_output],
+        )
+        prd_btn.click(
+            fn=transcribe,
+            inputs=[mic_input, upl_input],
+            outputs=[lbl_output],
+        )
+
+    demo.launch(debug=True)