app.py

import gradio as gr
from transformers import pipeline
import numpy as np

demo = gr.Blocks()

transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")

def transcribe_speech(filepath):
    if filepath is None:
        gr.Warning("No audio found, please retry.")
        return ""
    output = transcriber (filepath)
    return output["text"]

def transcribe_long_form(filepath):
    if filepath is None:
        gr.Warning("No audio found, please retry.")
        return ""
    output = transcriber(
      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"],
    )

# demo.launch(share=True, 
#             server_port=int(os.environ['PORT1']))

demo.launch()