metadata
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
license: apache-2.0
language:
- en
metrics:
- accuracy
base_model:
- microsoft/wavlm-large
pipeline_tag: audio-classification
WavLM-Large for Broader Accent Classification
Model Description
This model includes the implementation of broader 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: ['British Isles', 'North America', 'Other']
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-broader-accent").to(device)
model.eval()
Prediction
# Label List
english_accent_list = [
'British Isles', 'North America', 'Other'
]
# Load data, here just zeros as the example, audio data should be 16kHz mono channel
data = torch.zeros([1, 16000]).float().to(device)
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()])