add banner

app.py

@@ -39,8 +39,10 @@ tts_voice_list = asyncio.get_event_loop().run_until_complete(edge_tts.list_voice
 tts_voices = [f"{v['ShortName']}-{v['Gender']}" for v in tts_voice_list]
 
 # RVC models
-model_root = snapshot_download(repo_id="NoCrypt/miku_RVC", token=os.environ["TOKEN"])
-models = [d for d in os.listdir(model_root) if os.path.isdir(f"{model_root}/{d}")]
+model_root = snapshot_download(
+    repo_id="NoCrypt/miku_RVC", token=os.environ["TOKEN"])
+models = [d for d in os.listdir(
+    model_root) if os.path.isdir(f"{model_root}/{d}")]
 models.sort()
 
 
@@ -59,12 +61,14 @@ def model_data(model_name):
     version = cpt.get("version", "v1")
     if version == "v1":
         if if_f0 == 1:
-            net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=config.is_half)
+            net_g = SynthesizerTrnMs256NSFsid(
+                *cpt["config"], is_half=config.is_half)
         else:
             net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
     elif version == "v2":
         if if_f0 == 1:
-            net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=config.is_half)
+            net_g = SynthesizerTrnMs768NSFsid(
+                *cpt["config"], is_half=config.is_half)
         else:
             net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
     else:
@@ -129,7 +133,8 @@ def tts(
     print(tts_text)
     print(f"tts_voice: {tts_voice}, speed: {speed}")
     print(f"Model name: {model_name}")
-    print(f"F0: {f0_method}, Key: {f0_up_key}, Index: {index_rate}, Protect: {protect}")
+    print(
+        f"F0: {f0_method}, Key: {f0_up_key}, Index: {index_rate}, Protect: {protect}")
     try:
         t0 = time.time()
         if speed >= 0:
@@ -205,7 +210,7 @@ rmvpe_model = RMVPE("rmvpe.pt", config.is_half, config.device)
 print("rmvpe model loaded.")
 
 initial_md = """
-# Miku TTS
+![banner that says mikutts](https://huggingface.co/spaces/NoCrypt/mikuTTS/resolve/main/imgs/banner_mikutts.webp)
 """
 
 app = gr.Blocks()
@@ -214,13 +219,13 @@ with app:
     with gr.Row():
         with gr.Column():
             model_name = gr.Dropdown(
-                label="Model (all models except man-_ are girl models)",
+                label="Model",
                 choices=models,
                 value=models[0],
             )
             f0_key_up = gr.Number(
                 label="Tune (+12 = 1 octave up from edge-tts, the best value depends on the models and speakers)",
-                value=2,
+                value=6,
             )
         with gr.Column():
             f0_method = gr.Radio(
@@ -260,7 +265,8 @@ with app:
                 step=10,
                 interactive=True,
             )
-            tts_text = gr.Textbox(label="Input Text", value="これは日本語テキストから音声への変換デモです。")
+            tts_text = gr.Textbox(label="Input Text",
+                                  value="こんにちは、私の名前は初音ミクです!")
         with gr.Column():
             but0 = gr.Button("Convert", variant="primary")
             info_text = gr.Textbox(label="Output info")