minor edits on UI

README.md

@@ -11,7 +11,7 @@ license: cc-by-4.0
 short_description: 'Space to demo TTS models '
 ---
 
-# TWB Voice 1.0 - TTS Demo Space
+# TWB Voice - TTS Demo Space
 
 This Gradio demo showcases neural Text-to-Speech models developed within the TWB Voice project by CLEAR Global. Currently it supports **Hausa** and **Kanuri** languages, developed as part of the first phase of the project.
 

app.py

@@ -161,13 +161,13 @@ def synthesize_speech(text, language, speaker):
 # Create Gradio interface
 with gr.Blocks(title="TWB Voice TTS Demo") as demo:
     gr.Markdown("""
-    # TWB Voice 1.0 - Hausa & Kanuri Text-to-Speech
+    # TWB Voice Text-to-Speech Demo Space
     
-    This demo showcases neural Text-to-Speech models for **Hausa** and **Kanuri** languages, 
-    developed as part of the TWB Voice 1.0 project by CLEAR Global.
+    This demo showcases neural Text-to-Speech models developed within the TWB Voice project by CLEAR Global. 
+    Currently it supports **Hausa** and **Kanuri** languages, developed as part of the first phase of the project.
     
     ### Features:
-    - **Hausa**: 3 speakers (1 female, 2 male) - Kenanci dialect
+    - **Hausa**: 3 speakers (1 female, 2 male)
     - **Kanuri**: 1 female speaker
     - High-quality 24kHz audio output
     - Based on YourTTS architecture
@@ -209,7 +209,7 @@ with gr.Blocks(title="TWB Voice TTS Demo") as demo:
             )
             
             # Example buttons
-            gr.Markdown("**Quick examples:**")
+            gr.Markdown("**Quick examples (press to load):**")
             with gr.Row():
                 example_btn_1 = gr.Button("Example 1", size="sm")
                 example_btn_2 = gr.Button("Example 2", size="sm")
@@ -265,14 +265,11 @@ with gr.Blocks(title="TWB Voice TTS Demo") as demo:
     gr.Markdown("""
     ---
     ### Notes:
-    - Models work best with **lowercase input text** (automatically converted)
-    - **Hausa model** supports diacritics: `ăāɓɗƙƴū`
-    - **Kanuri model** supports diacritics: `áúǝəә`
+    - Models work with **lowercase input text** (automatically converted)
     - Audio output is generated at 24kHz sample rate
-    - Models are optimized for educational and general content
     
     ### License:
-    These models are released under **CC-BY-NC-4.0** license (Non-Commercial use only).
+    This app and the models are released under **CC-BY-NC-4.0** license (Non-Commercial use only).
     
     **Created by:** CLEAR Global with support from the Patrick J. McGovern Foundation
     """)