app.py

import gradio as gr
from transformers import pipeline
import numpy as np

transcriber = pipeline("automatic-speech-recognition", model="Reihaneh/wav2vec2_frisian_common_voice_1")

def transcribe(audio):
    sr, y = audio
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))

    return transcriber({"sampling_rate": 16000, "raw": y})["text"]


demo = gr.Interface(
    transcribe,
    gr.Audio(sources=["upload"]),
    "text",
)

demo.launch()