app.py

from transformers import pipeline
import gradio as gr

pipe = pipeline(model="jbatista79/whisper-jrb-small-es")  # change to "your-username/the-name-you-picked"

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

iface = gr.Interface(
    fn=transcribe,
    # inputs=gr.Audio(source="microphone", type="filepath"),
    inputs=gr.Audio(sources=["microphone"], type="filepath"),
    outputs="text",
    title="Whisper Small Spanish - JRB",
    description="Realtime proof-of-concept demo for Spanish speech recognition using a fine-tuned Whisper small model. Created by Josué R. Batista - 2024-01-14",
)

iface.launch(share=True)