app.py

import gradio as gr
from transformers import pipeline

checkpoint = "openai/whisper-small"

pipe = pipeline(model=checkpoint)


def transcribe(microphone, file_upload):
    warn_output = ""
    if (microphone is not None) and (file_upload is not None):
        warn_output = "WARNING: You've uploaded an audio file and used the microphone. " \
                      "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
        file = microphone

    elif (microphone is None) and (file_upload is None):
        return "ERROR: You have to either use the microphone or upload an audio file"

    file = microphone if microphone is not None else file_upload
    
    text = pipe(file)["text"]

    return warn_output + text


iface = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.inputs.Audio(source="microphone", type='filepath', optional=True),
        gr.inputs.Audio(source="upload", type='filepath', optional=True),
    ],
    outputs="text",
    layout="horizontal",
    theme="huggingface",
    title="Whisper Speech Recognition Demo",
    description=f"Demo for speech recognition using the fine-tuned checkpoint: [{checkpoint}](https://huggingface.co/{checkpoint}).",
    allow_flagging='never',
)

iface.launch(enable_queue=True)