app.py

from transformers.utils import logging
logging.set_verbosity_error()
# from datasets import load_dataset
from transformers import pipeline
import gradio as gr

# dataset = load_dataset("librispeech_asr",
#                        split="train.clean.100",
#                        streaming=True,
#                        trust_remote_code=True)

asr = pipeline(task="automatic-speech-recognition",
               model="openai/whisper-small")

demo = gr.Blocks()

def transcribe_long_form(filepath):
    if filepath is None:
        gr.Warning("No audio found, please retry.")
        return ""
    output = asr(
      filepath,
      max_new_tokens=256,
      chunk_length_s=30,
      batch_size=8,
    )
    return output["text"]

mic_transcribe = gr.Interface(
    fn=transcribe_long_form,
    inputs=gr.Audio(sources="microphone",
                    type="filepath"),
    outputs=gr.Textbox(label="Transcription",
                       lines=3),
    allow_flagging="never")

file_transcribe = gr.Interface(
    fn=transcribe_long_form,
    inputs=gr.Audio(sources="upload",
                    type="filepath"),
    outputs=gr.Textbox(label="Transcription",
                       lines=3),
    allow_flagging="never",
)

with demo:
    gr.TabbedInterface(
        [mic_transcribe,
         file_transcribe],
        ["Transcribe Microphone",
         "Transcribe Audio File"], title= "Automatic Speech Recognition"
    )
demo.launch(share=True)