app.py

# !pip install transformers
# !pip install -U datasets
# !pip install soundfile
# !pip install librosa
# !pip install gradio

from transformers.utils import logging
logging.set_verbosity_error()

from datasets import load_dataset

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

from transformers import pipeline
asr = pipeline(task="automatic-speech-recognition",
               model="distil-whisper/distil-small.en")

asr.feature_extractor.sampling_rate


import os
import gradio as gr

demo = gr.Blocks()

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

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


file_transcribe = gr.Interface( fn=transcribe_speech,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)