aspram-realtime / app.py
yerevann's picture
Update app.py
431e082
from transformers import pipeline
import gradio as gr
import time
asr = pipeline("automatic-speech-recognition", "YSU/aspram")
def transcribe(audio, state=None):
if state is None:
state = ""
# time.sleep(5)
text = asr(audio)["text"]
state += text + " "
print('chunk!')
return state, state
gr.Interface(
fn=transcribe,
inputs=[
gr.inputs.Audio(source="microphone", type="filepath"),
"state"
],
outputs=[
"textbox",
"state"
],
live=False,
css='body {background-color: rgba(240, 200, 192)}',
).launch()