00-01_voice2text.py

import whisper
import gradio as gr 
import time
from pyChatGPT import ChatGPT
import warnings
from gtts import gTTS


warnings.filterwarnings("ignore")
# model = whisper.load_model("base")
model = whisper.load_model("base")

def transcribe(audio):

    # load audio and pad/trim it to fit 30 seconds
    audio = whisper.load_audio(audio)
    audio = whisper.pad_or_trim(audio)

    # make log-Mel spectrogram and move to the same device as the model
    mel = whisper.log_mel_spectrogram(audio).to(model.device)

    # decode the audio
    options = whisper.DecodingOptions(fp16=False)
    result = whisper.decode(model, mel, options)
    result_text = result.text

    # print the result
    return result_text

output_1 = gr.Textbox(label="Speech to Text")

gr.Interface(
    title = 'Voice to Text (KF)', 
    fn=transcribe, 
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath")
    ],

    outputs=[
        output_1
    ],
    live=True, allow_flagging=False).launch(share=False)