app.py

import gradio as gr
from transformers import pipeline

# Load Whisper model from Hugging Face
# This uses the `transformers` library's pipeline to load the model
transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")

def transcribe(audio):
    # Transcribe the audio using the Whisper model
    result = transcriber(audio)["text"]
    return result

# Create a Gradio Interface
interface = gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(sources="upload", type="filepath"), 
    outputs="text",
    title="Whisper Speech-to-Text API",
    description="Upload an audio file and get a transcription using OpenAI's Whisper model from Hugging Face."
)

# Launch the interface as an API
interface.launch()