Spaces:
Running
Running
File size: 2,113 Bytes
722f78c cab3c84 722f78c 438f5e6 722f78c 438f5e6 722f78c |
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 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
import os
import uuid
import torch
import requests
import gradio as gr
from moviepy import VideoFileClip
from speechbrain.pretrained.interfaces import foreign_class
# Load the pretrained model
classifier = foreign_class(
source="Jzuluaga/accent-id-commonaccent_xlsr-en-english",
pymodule_file="custom_interface.py",
classname="CustomEncoderWav2vec2Classifier"
)
def extract_audio(video_path, output_wav="output.wav"):
video = VideoFileClip(video_path)
audio = video.audio
audio.write_audiofile(output_wav, codec='pcm_s16le', fps=16000)
return output_wav
def download_video(url, filename="temp.mp4"):
response = requests.get(url, stream=True)
with open(filename, 'wb') as f:
for chunk in response.iter_content(chunk_size=8192):
f.write(chunk)
return filename
def classify_video_accent(video_url):
uid = str(uuid.uuid4())
video_path = f"{uid}.mp4"
wav_path = f"{uid}.wav"
try:
download_video(video_url, video_path)
extract_audio(video_path, wav_path)
out_prob, score, index, text_lab = classifier.classify_file(wav_path)
confidence = torch.max(out_prob).item() * 100
return {
"accent": text_lab,
"confidence_score": f"{confidence:.2f}%",
"summary": f"The speaker is most likely using a(n) {text_lab} English accent."
}
finally:
for f in [video_path, wav_path]:
if os.path.exists(f):
os.remove(f)
def gradio_accent_classifier(video_url):
try:
result = classify_video_accent(video_url)
return f"""Accent: {result['accent']}
Confidence: {result['confidence_score']}
Summary: {result['summary']}"""
except Exception as e:
return f"Error: {str(e)}"
iface = gr.Interface(
fn=gradio_accent_classifier,
inputs=gr.Textbox(label="Public .mp4 Video URL"),
outputs="text",
title="English Accent Classifier",
description="Paste a direct link to a public .mp4 file to classify the English accent spoken in the video."
)
if __name__ == "__main__":
iface.launch()
|