app.py

import gradio as gr
from faster_whisper import WhisperModel

model_size = "large-v2"

model = WhisperModel(model_size, device="cpu", compute_type="int8")


def transcribe(audio, state=""):
    print(audio)
    segments, info = model.transcribe(audio, beam_size=5)

    print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

    for segment in segments:
        print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
        state += segment.text + " "

    return state, state


gr.Interface(
    fn=transcribe,
    inputs=[
        gr.Audio(source="microphone", type="filepath", streaming=True),
        "state"
    ],
    outputs=[
        "textbox",
        "state"
    ],
    live=True).launch()