Update app.py

app.py

@@ -100,7 +100,12 @@ E2TTS_ema_model = load_model(
 E2TTS_ema_model2 = load_model(
     "Gregniuki", "F5-tts_English_German_Polish", "Polish", DiT, F5TTS_model_cfg, 500000
 )
-
+E2TTS_ema_model3 = load_model(
+    "SWivid", "F5-TTS", "F5TTS_Base", DiT, F5TTS_model_cfg, 1200000
+)
+E2TTS_ema_model4 = load_model(
+    "SWivid", "E2-TTS", "E2TTS_Base", DiT, E2TTS_model_cfg, 1200000
+)
 def chunk_text(text, max_chars=135):
     """
     Splits the input text into chunks, each with a maximum number of characters.
@@ -138,6 +143,10 @@ def infer_batch(ref_audio, ref_text, gen_text_batches, exp_name, remove_silence,
         ema_model = E2TTS_ema_model
     elif exp_name == "Deutsh":
         ema_model = E2TTS_ema_model2
+    elif exp_name == "F5TTS":
+        ema_model = E2TTS_ema_model3
+    elif exp_name == "E2TTS":
+        ema_model = E2TTS_ema_model4
 
     audio, sr = ref_audio
     if audio.shape[0] > 1:
@@ -404,7 +413,7 @@ with gr.Blocks() as app_tts:
     ref_audio_input = gr.Audio(label="Reference Audio", type="filepath")
     gen_text_input = gr.Textbox(label="Text to Generate", lines=10)
     model_choice = gr.Radio(
-        choices=["English","Polish","Deutsh"], label="Choose TTS Model", value="English"
+        choices=["English","Polish","Deutsh","F5TTS","E2TTS"], label="Choose TTS Model", value="English"
     )
     generate_btn = gr.Button("Synthesize", variant="primary")
     with gr.Accordion("Advanced Settings", open=False):
@@ -598,7 +607,7 @@ with gr.Blocks() as app_emotional:
 
     # Model choice
     model_choice_emotional = gr.Radio(
-        choices=["English","Polish","Deutsh"], label="Choose TTS Model", value="English"
+        choices=["English","Polish","Deutsh","F5TTS","E2TTS"], label="Choose TTS Model", value="English"
     )
 
     with gr.Accordion("Advanced Settings", open=False):