Upload 3 files

app.py

@@ -1,16 +1,12 @@
 import torch
-
 import gradio as gr
 import pytube as pt
 from transformers import pipeline
 from diffusers import StableDiffusionPipeline
 
 
-
 MODEL_NAME = "whispy/whisper_italian"
 
-device = 0 if torch.cuda.is_available() else "cpu"
-
 summarizer = pipeline(
     "summarization",
     model="it5/it5-efficient-small-el32-news-summarization",
@@ -20,13 +16,12 @@ pipe = pipeline(
     task="automatic-speech-recognition",
     model=MODEL_NAME,
     chunk_length_s=30,
-    device=device,
+    device="cpu",
 )
 
 YOUR_TOKEN="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"
 image_pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", revision="fp16", torch_dtype=torch.float16, use_auth_token=YOUR_TOKEN)
-
-image_pipe.to("cuda")
+image_pipe.to("cpu")
 
 translator = pipeline("translation", model="Helsinki-NLP/opus-mt-it-en")