Update app.py

app.py

@@ -4,30 +4,18 @@ import numpy as np
 
 transcriber = pipeline("automatic-speech-recognition")
 
-def generate_img(promt):
-  print(promt)
-  model_id = "stabilityai/stable-diffusion-2-1"
-  pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
-  pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
-  #pipe = pipe.to("cuda")
-  #pipe = pipe.to("cpu")
-  pic = pipe(promt).images[0]
-  return pic
-
 def transcribe(audio):
     sr, y = audio
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))
-    txt= transcriber({"sampling_rate": sr, "raw": y})["text"]
-    #txt="dog with a hat"
-    img= generate_img(txt)
-    return  txt, img
 
-g_image = gr.Interface(
+    return transcriber({"sampling_rate": sr, "raw": y})["text"]
+
+demo = gr.Interface(
     transcribe,
-    inputs=gr.Audio(sources=["microphone"], type="numpy", label="xerra aqui..."),
-    outputs=[gr.Textbox(label="Promt",info="La transcripció de la grabació feta",lines=2), "image"]
+    gr.Audio(sources=["microphone"], type="numpy", label="xerra aqui..."),
+    "text",
 )
 
+demo.launch(debug=True)
 
-g_image.launch(debug=True, share=True)