Add GitHub repo and clean

app.py

@@ -1,14 +1,16 @@
+import asyncio
+import datetime
+import logging
 import os
-import torch
+import time
+import traceback
 
-# os.system("wget -P cvec/ https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt")
+import edge_tts
 import gradio as gr
 import librosa
-import numpy as np
-import logging
+import torch
 from fairseq import checkpoint_utils
-from vc_infer_pipeline import VC
-import traceback
+
 from config import Config
 from lib.infer_pack.models import (
     SynthesizerTrnMs256NSFsid,
@@ -16,15 +18,10 @@ from lib.infer_pack.models import (
     SynthesizerTrnMs768NSFsid,
     SynthesizerTrnMs768NSFsid_nono,
 )
-import asyncio
-import edge_tts
-import time
-import datetime
-
 from rmvpe import RMVPE
+from vc_infer_pipeline import VC
 
 logging.getLogger("fairseq").setLevel(logging.WARNING)
-
 logging.getLogger("numba").setLevel(logging.WARNING)
 logging.getLogger("markdown_it").setLevel(logging.WARNING)
 logging.getLogger("urllib3").setLevel(logging.WARNING)
@@ -82,7 +79,7 @@ def model_data(model_name):
     else:
         net_g = net_g.float()
     vc = VC(tgt_sr, config)
-    n_spk = cpt["config"][-3]
+    # n_spk = cpt["config"][-3]
 
     index_files = [
         f"{model_root}/{model_name}/{f}"
@@ -220,7 +217,8 @@ Input text ➡[(edge-tts)](https://github.com/rany2/edge-tts)➡ Speech mp3 file
 Although the models are trained on Japanese voices and intended for Japanese text, they can also be used with other languages with the corresponding edge-tts speaker (but possibly with a Japanese accent).
 
 Input characters are limited to 280 characters, and the speech audio is limited to 20 seconds in this 🤗 space.
-Run locally for longer audio.
+
+[Visit this GitHub repo](https://github.com/litagin02/rvc-tts-webui) for running locally with your models!
 """
 
 app = gr.Blocks()