Update app.py

app.py

@@ -9,7 +9,6 @@ import logging
 import soundfile
 import asyncio
 import argparse
-import edge_tts
 import gradio.processing_utils as gr_processing_utils
 logging.getLogger('numba').setLevel(logging.WARNING)
 logging.getLogger('markdown_it').setLevel(logging.WARNING)
@@ -29,21 +28,7 @@ def audio_postprocess(self, y):
 
 gr.Audio.postprocess = audio_postprocess
 def create_vc_fn(model, sid):
-    def vc_fn(input_audio, vc_transform, auto_f0, tts_text, tts_voice, tts_mode):
-        if tts_mode:
-            if len(tts_text) > 100 and limitation:
-                return "Text is too long", None
-            if tts_text is None or tts_voice is None:
-                return "You need to enter text and select a voice", None
-            asyncio.run(edge_tts.Communicate(tts_text, "-".join(tts_voice.split('-')[:-1])).save("tts.mp3"))
-            audio, sr = librosa.load("tts.mp3", sr=16000, mono=True)
-            raw_path = io.BytesIO()
-            soundfile.write(raw_path, audio, 16000, format="wav")
-            raw_path.seek(0)
-            out_audio, out_sr = model.infer(sid, vc_transform, raw_path,
-                                            auto_predict_f0=auto_f0,
-                                            )
-            return "Success", (44100, out_audio.cpu().numpy())
+    def vc_fn(input_audio, vc_transform, auto_f0):
         if input_audio is None:
             return "You need to upload an audio", None
         sampling_rate, audio = input_audio
@@ -73,9 +58,6 @@ if __name__ == '__main__':
     hubert_model = utils.get_hubert_model().to(args.device)
     models = []
     voices = []
-    tts_voice_list = asyncio.get_event_loop().run_until_complete(edge_tts.list_voices())
-    for r in tts_voice_list:
-        voices.append(f"{r['ShortName']}-{r['Gender']}")
     for f in os.listdir("models"):
         name = f
         model = Svc(fr"models/{f}/{f}.pth", f"models/{f}/config.json", device=args.device)
@@ -102,14 +84,10 @@ if __name__ == '__main__':
                             vc_input = gr.Audio(label="Input audio"+' (less than 20 seconds)' if limitation else '')
                             vc_transform = gr.Number(label="vc_transform", value=0)
                             auto_f0 = gr.Checkbox(label="auto_f0", value=False)
-                            tts_mode = gr.Checkbox(label="tts (use edge-tts as input)", value=False)
-                            tts_text = gr.Textbox(visible=False, label="TTS text (100 words limitation)" if limitation else "TTS text")
-                            tts_voice = gr.Dropdown(choices=voices, visible=False)
-                            vc_submit = gr.Button("Generate", variant="primary")
                         with gr.Column():
                             vc_output1 = gr.Textbox(label="Output Message")
                             vc_output2 = gr.Audio(label="Output Audio")
-                vc_submit.click(vc_fn, [vc_input, vc_transform, auto_f0, tts_text, tts_voice, tts_mode], [vc_output1, vc_output2])
+                vc_submit.click(vc_fn, [vc_input, vc_transform, auto_f0], [vc_output1, vc_output2])
             
             """
             for category, link in others.items():