tiantiaf/wavlm-large-narrow-accent

WavLM-Large for Narrow Accent Classification

Model Description

This model includes the implementation of narrow accent classification described in Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits (https://arxiv.org/pdf/2505.14648)

The included English accents are:

[
  'East Asia', 'English', 'Germanic', 'Irish', 
  'North America', 'Northern Irish', 'Oceania', 
  'Other', 'Romance', 'Scottish', 'Semitic', 'Slavic', 
  'South African', 'Southeast Asia', 'South Asia', 'Welsh'
]

• Library: https://github.com/tiantiaf0627/vox-profile-release

How to use this model

Download repo

git clone [email protected]:tiantiaf0627/vox-profile-release.git

Install the package

conda create -n vox_profile python=3.8
cd vox-profile-release
pip install -e .

Load the model

# Load libraries
import torch
import torch.nn.functional as F
from src.model.accent.wavlm_accent import WavLMWrapper

# Find device
device = torch.device("cuda") if torch.cuda.is_available() else "cpu"

# Load model from Huggingface
model = WavLMWrapper.from_pretrained("tiantiaf/wavlm-large-narrow-accent").to(device)
model.eval()

Prediction

# Label List
english_accent_list = [
    'East Asia', 'English', 'Germanic', 'Irish', 
    'North America', 'Northern Irish', 'Oceania', 
    'Other', 'Romance', 'Scottish', 'Semitic', 'Slavic', 
    'South African', 'Southeast Asia', 'South Asia', 'Welsh'
]
    
# Load data, here just zeros as the example
# Our training data filters output audio shorter than 3 seconds (unreliable predictions) and longer than 15 seconds (computation limitation)
# So you need to prepare your audio to a maximum of 15 seconds, 16kHz and mono channel
max_audio_length = 15 * 16000
data = torch.zeros([1, 16000]).float().to(device)[:, :max_audio_length]
logits, embeddings = model(data, return_feature=True)
    
# Probability and output
accent_prob = F.softmax(logits, dim=1)
print(english_accent_list[torch.argmax(accent_prob).detach().cpu().item()])

If you have any questions, please contact: Tiantian Feng ([email protected])

Kindly cite our paper if you are using our model or find it useful in your work

@article{feng2025vox,
  title={Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits},
  author={Feng, Tiantian and Lee, Jihwan and Xu, Anfeng and Lee, Yoonjeong and Lertpetchpun, Thanathai and Shi, Xuan and Wang, Helin and Thebaud, Thomas and Moro-Velazquez, Laureano and Byrd, Dani and others},
  journal={arXiv preprint arXiv:2505.14648},
  year={2025}
}

❌ Out-of-Scope Use

• Clinical or diagnostic applications
• Surveillance
• Privacy-invasive applications
• No commercial use