app.py

import torch

import gradio as gr
import pytube as pt
from transformers import pipeline
from huggingface_hub import model_info

MODEL_NAME = "openai/whisper-small" #this always needs to stay in line 8 :D sorry for the hackiness
lang = "en"

device = 0 if torch.cuda.is_available() else "cpu"
pipe = pipeline(
    task="automatic-speech-recognition",
    model=MODEL_NAME,
    chunk_length_s=30,
    device=device,
)

pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")

def transcribe(microphone, file_upload):
    warn_output = ""
    if (microphone is not None) and (file_upload is not None):
        warn_output = (
            "WARNING: You've uploaded an audio file and used the microphone. "
            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
        )

    elif (microphone is None) and (file_upload is None):
        return "ERROR: You have to either use the microphone or upload an audio file"

    file = microphone if microphone is not None else file_upload

    text = pipe(file)["text"]

    return warn_output + text

demo = gr.Blocks()

examples = [
    ['TestAudio1.mp3'], ['TestAudio2.wav'], ['TestAudio3.wav'], ['TestAudio4.wav'], ['TestAudio5.wav'], ['TestAudio6.wav'], ['TestAudio7.wav'], ['TestAudio8.wav'], ['TestAudio9.wav'], ['TestAudio10.wav']
]

mf_transcribe = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
        gr.inputs.Audio(source="upload", type="filepath", optional=True)
    ],
    outputs="text",
    layout="horizontal",
    theme="huggingface",
    allow_flagging="never",
    examples = examples
).launch(enable_queue=True)

#used openai/whisper model