import gradio as gr

import nemo.collections.asr as nemo_asr


asr_model = nemo_asr.models.EncDecCTCModelBPE. \
                    from_pretrained("theodotus/stt_uk_squeezeformer_ctc_xs",map_location="cpu")



def transcribe(audio, state=""):
    text = asr_model.transcribe([audio], batch_size=1)[0]
    state += text + " "
    return state, state


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