app.py

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
import gradio as gr

device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "distil-whisper/distil-small.en"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    torch_dtype=torch_dtype,
    device=device,
)

def audio2text(audio_file):
  output=pipe(audio_file)
  return output['text']

gr.Interface(fn=audio2text, inputs=[gr.Audio(label='upload your audio file', sources='upload', type='filepath')], outputs=[gr.Textbox(label="transcription")]).launch()