Update vc.py

vc.py

@@ -3,7 +3,6 @@ import torch
 from pathlib import Path
 from pytube import YouTube
 from pydub import AudioSegment
-from transformers import AutoProcessor, BarkModel
 from TTS.api import TTS
 import uuid
 import os
@@ -11,36 +10,7 @@ import os
 test_audio="./shufflin.wav"
 
 uid = uuid.uuid4()
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-processor = AutoProcessor.from_pretrained("suno/bark-small")
-model = BarkModel.from_pretrained("suno/bark-small").to(device)
-num_list = ["1","2","3","4","5","6","7","8","9","10"]
-lang_list = ["en","de"]
-#SAMPLE_RATE = 24_000
-def run_bark(text, n='1', lang='en'):
-    uid=uuid.uuid4()
-    #history_prompt = []
-    semantic_prompt=f"v2/{lang}_speaker_{int(n)-1}"
-
-        #text=["Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."],
-    inputs = processor(text=text,
-        voice_preset = semantic_prompt,
-        return_tensors="pt",
-    )
-    print("generating")
-    speech_values = model.generate(
-        **inputs, coarse_temperature = 0.8, temperature = 0.5, do_sample=True
-    )
-    #speech_values = model.generate(**inputs, do_sample=True)
-    sampling_rate = model.generation_config.sample_rate
-
-    #sampling_rate = 24_000
-    print("writing")
-    scipy.io.wavfile.write(f"bark_out-{uid}.wav", rate=sampling_rate, data=speech_values.cpu().numpy().squeeze())
-    return (f"bark_out-{uid}.wav")
-
+device="cpu"
 
 
 def custom_bark(inp, tog, in_aud=None, trim_aud=None, in_aud_mic=None):