app.py

import torch
from transformers import pipeline
import gradio as gr

MODEL_NAME = "Shamik/distil-whisper-small-polyAI-minds14"

pipe = pipeline(
    task="automatic-speech-recognition",
    model=MODEL_NAME,
    chunk_length_s=30,
)

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

demo = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.Audio(sources="upload", label="Audio file", type="filepath"),
    ],
    outputs="text",
    title="Distil Whisper English Speech Transcription",
    description=(
        "Transcribe long-form audio inputs with the click of a button! Demo uses the"
        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
        " of arbitrary length."
    ),
    examples=[
        ["./example2.flac"],
        ["./example0.flac"],
    ],
    cache_examples=True,
    allow_flagging="never",
)

demo.launch()