from transformers import pipeline
import gradio as gr
import torch

def detect_gpu():
    if not torch.cuda.is_available():
        print("No GPU device found")
        exit()
    
    print(f"Found {torch.cuda.device_count()} GPU device(s)")
    print(f"Using {torch.cuda.get_device_name(0)}")
    
detect_gpu()

pipe = pipeline(model="pierrelf/whisper-small-sv", device=0)

def transcribe(audio):
    text = pipe(audio)["text"]
    return text

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=['upload', 'microphone'], type="filepath"),
    outputs="text",
    title="Whisper Swedish",
    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",
)

iface.launch(server_name="0.0.0.0")