Update app.py

app.py

@@ -19,11 +19,11 @@ feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)
 SAMPLE_RATE = feature_extractor.sampling_rate
 SEED = 42
 
-default_text = "*Remember* - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of *five times*."
+default_text = "*Remember* - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, I am scaling up the amount of *training data*."
 default_description = "Thomas speaks with emphasis and excitement at a moderate pace with high quality."
 examples = [
     [
-        "Remember - this is only the first iteration of the model. To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
+        "*Remember* - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, I am scaling up the amount of *training data*.",
         "Thomas speaks in a sad tone at a moderate pace with high quality."
     ],
     [
@@ -124,7 +124,7 @@ with gr.Blocks(css=css) as block:
                 "
               >
                 <h1 style="font-weight: 900; margin-bottom: 7px; line-height: normal;">
-                  SML Emotional Text to Speech Project
+                  SML Emotional TTS- Hiring Project Assignment
                 </h1>
               </div>
             </div>
@@ -132,6 +132,10 @@ with gr.Blocks(css=css) as block:
     )
     gr.HTML(
         f"""
+        <p><a href="https://huggingface.co/parler-tts/parler-tts-mini-expresso"> Parler-TTS Mini: Expresso</a>
+        is a text-to-speech (TTS) model fine-tuned on the <a href="https://huggingface.co/datasets/ylacombe/expresso"> Expresso dataset</a>.
+        It generates high-quality speech in a given <b>emotion</b> and <b>voice</b> that can be controlled through a simple text prompt.</p>
+
         <p>Tips for ensuring good generation:
         <ul>
             <li>Specify the name of a male speaker (Jerry, Thomas) or female speaker (Talia, Elisabeth) for consistent voices</li>
@@ -154,6 +158,11 @@ with gr.Blocks(css=css) as block:
     outputs = [audio_out]
     gr.Examples(examples=examples, fn=gen_tts, inputs=inputs, outputs=outputs, cache_examples=True)
     run_button.click(fn=gen_tts, inputs=inputs, outputs=outputs, queue=True)
+    gr.HTML(
+        """
+        <p></p>
+        """
+    )
 
 block.queue()
 block.launch(share=True)