Update app.py

app.py

@@ -220,6 +220,27 @@ def run(seed, left_margin, right_margin, codec_audio_sr, codec_sr, top_k, top_p,
         audio_path, transcribe_state, transcript, smart_transcript,
         mode, prompt_end_time, edit_start_time, edit_end_time,
         split_text, selected_sentence, previous_audio_tensors):
+    
+    voicecraft_model_name = "830M_TTSEnhanced"
+
+    voicecraft_name = f"{voicecraft_model_name}.pth"
+    model = voicecraft.VoiceCraft.from_pretrained(f"pyp1/VoiceCraft_{voicecraft_name.replace('.pth', '')}")
+    phn2num = model.args.phn2num
+    config = model.args
+    model.to(device)
+
+    encodec_fn = f"{MODELS_PATH}/encodec_4cb2048_giga.th"
+    if not os.path.exists(encodec_fn):
+        os.system(f"wget https://huggingface.co/pyp1/VoiceCraft/resolve/main/encodec_4cb2048_giga.th -O " + encodec_fn)
+
+    voicecraft_model = {
+        "config": config,
+        "phn2num": phn2num,
+        "model": model,
+        "text_tokenizer": TextTokenizer(backend="espeak"),
+        "audio_tokenizer": AudioTokenizer(signature=encodec_fn)
+    }
+
     if voicecraft_model is None:
         raise gr.Error("VoiceCraft model not loaded")
     if smart_transcript and (transcribe_state is None):
@@ -617,4 +638,4 @@ if __name__ == "__main__":
     MODELS_PATH = args.models_path
 
     app = get_app()
-    app.queue().launch(share=args.share, server_port=args.port)
+    app.queue().launch(share=args.share, server_port=args.port)