app.py

from transformers import pipeline
from transformers import  WhisperProcessor, WhisperForConditionalGeneration
import gradio as gr

model = WhisperForConditionalGeneration.from_pretrained("MaximilianChen/Casper")
processor = WhisperProcessor.from_pretrained("MaximilianChen/Casper", language='catalan', task='transcribe')
asr = pipeline("automatic-speech-recognition", model=model, pprocessor=processor)

def transcribe_audio(mic=None, file=None):
    if mic is not None:
        audio = mic
    elif file is not None:
        audio = file
    else:
        return "You must either provide a mic recording or a file"
    transcription = asr(audio)["text"]
    return transcription


gr.Interface(
    fn=transcribe_audio,
    inputs=[
        gr.Audio(source="microphone", type="filepath", optional=True),
        gr.Audio(source="upload", type="filepath", optional=True),
    ],
    outputs="text",
).launch()