feat: customisations

app.py

@@ -74,15 +74,14 @@ def inference(audio, sentiment_option):
 title = """<h1 align="center">☕ Lim Kopi 💬</h1>"""
 image_path = "coffee_logo.jpg"
 description = """
-💻 This demo showcases a general-purpose speech recognition model called Whisper. It is trained on a large dataset of diverse audio and supports multilingual speech recognition, speech translation, and language identification tasks.<br><br>
-<br>
-⚙️ Components of the tool:<br>
+💻 This MVP shows how we can use Whisper to conduct audio sentiment analysis on voice recordings of customer service agents. Whisper is a general speech recognition model built by OpenAI. It is trained on a large dataset of diverse audio and supports multilingual speech recognition, speech translation, and language identification tasks.<br><br>
+⚙️ MVP Components:<br>
 <br>
 &nbsp;&nbsp;&nbsp;&nbsp; - Real-time multilingual speech recognition<br>
 &nbsp;&nbsp;&nbsp;&nbsp; - Language identification<br>
 &nbsp;&nbsp;&nbsp;&nbsp; - Sentiment analysis of the transcriptions<br>
 <br>
-🎯 The sentiment analysis results are provided as a dictionary with different emotions and their corresponding scores.<br>
+🎯 The sentiment analysis results are provided as a dictionary with different emotions and their corresponding scores, so customer service agents can receive feedback on the overall call quality and customer receptiveness.<br>
 <br>
 
 😃 The sentiment analysis results are displayed with emojis representing the corresponding sentiment.<br>
@@ -94,7 +93,7 @@ description = """
 ❓ Use the microphone for real-time speech recognition.<br>
 <br>
 
-⚡️ The model will transcribe the audio and perform sentiment analysis on the transcribed text.<br>
+⚡️ The model will transcribe the audio for record-keeping, and perform sentiment analysis on the transcribed text.<br>
 
 """
 
@@ -108,9 +107,12 @@ custom_css = """
     font-size: 14px;
     min-height: 300px;
 }
+.svelte-1mwvhlq {
+    display: none !important;
+}
 """
 
-block = gr.Blocks(css=custom_css)
+block = gr.Blocks(title="Lim Kopi Call Center Service", css=custom_css)
 
 with block:
     gr.HTML(title)
@@ -123,34 +125,23 @@ with block:
 
     with gr.Group():
         with gr.Box():
-            audio = gr.Audio(
-                label="Input Audio",
-                show_label=False,
-                source="microphone",
-                type="filepath"
-            )
-
             sentiment_option = gr.Radio(
                 choices=["Sentiment Only", "Sentiment + Score"],
                 label="Select an option",
-                default="Sentiment Only"
             )
-
+            audio = gr.Audio(
+                source="microphone",
+                type="filepath"
+            )
+        with gr.Box():
             btn = gr.Button("Transcribe")
 
         lang_str = gr.Textbox(label="Language")
 
         text = gr.Textbox(label="Transcription")
 
-        sentiment_output = gr.Textbox(label="Sentiment Analysis Results", output=True)
+        sentiment_output = gr.Textbox(label="Sentiment Analysis Results")
 
         btn.click(inference, inputs=[audio, sentiment_option], outputs=[lang_str, text, sentiment_output])
 
-        gr.HTML('''
-        <div class="footer">
-            <p>Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a>
-            </p>
-        </div>
-        ''') 
-
 block.launch()