Spaces:
Running
Running
File size: 1,526 Bytes
34aa4f5 54dc27b 34aa4f5 54dc27b 34aa4f5 03cbfbf 34aa4f5 f46c081 34aa4f5 9e66cfd 34aa4f5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
from transformers import pipeline
import gradio as gr
import time
import unicodedata
p = pipeline("automatic-speech-recognition",model="kingabzpro/wav2vec2-large-xls-r-300m-Urdu")
def transcribe(audio, state=""):
time.sleep(2)
text = p(audio)["text"]
state += unicodedata.normalize("NFC",text) + " "
return state, state
################### Gradio Web APP ################################
title = "Real-Time Urdu ASR"
description = """
<p>
<center>
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset.
</center>
</p>
<center>
<img src="https://huggingface.co/spaces/kingabzpro/real-time-Urdu-ASR/resolve/main/Images/cover.jpg" alt="logo" width="550"/>
</center>
"""
article = "<p style='text-align: center'><a href='https://dagshub.com/kingabzpro/Urdu-ASR-SOTA' target='_blank'>Source Code on DagsHub</a></p><p style='text-align: center'><a href='https://huggingface.co/blog/fine-tune-xlsr-wav2vec2' target='_blank'>Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers</a></p></center><center><img src='https://visitor-badge.glitch.me/badge?page_id=kingabzpro/real-time-Urdu-ASR' alt='visitor badge'></center></p>"
gr.Interface(
fn=transcribe,
inputs=[
gr.Audio(source="microphone", type="filepath", streaming=True),
"state"
],
outputs=[
"textbox",
"state"
],
title=title,
description=description,
article=article,
theme='EveryPizza/Cartoony-Gradio-Theme',
live=True).launch()
|