Hubert Base Superb Sid

🚀 Hubert-Base for Speaker Identification

This model is designed for speaker identification, leveraging the Hubert architecture to classify speaker identities in speech audio.

🚀 Quick Start

You can quickly start using this model through the following code examples.

✨ Features

• Ported Version: This is a ported version of S3PRL's Hubert for the SUPERB Speaker Identification task.
• Base Model: The base model is hubert-base-ls960, pretrained on 16kHz sampled speech audio.
• Task and Dataset: It is used for the Speaker Identification (SI) task, adopting the widely used VoxCeleb1 dataset.

📦 Installation

The original document does not provide installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

from datasets import load_dataset
from transformers import pipeline

dataset = load_dataset("anton-l/superb_demo", "si", split="test")

classifier = pipeline("audio-classification", model="superb/hubert-base-superb-sid")
labels = classifier(dataset[0]["file"], top_k=5)

Advanced Usage

import torch
import librosa
from datasets import load_dataset
from transformers import HubertForSequenceClassification, Wav2Vec2FeatureExtractor

def map_to_array(example):
    speech, _ = librosa.load(example["file"], sr=16000, mono=True)
    example["speech"] = speech
    return example

# load a demo dataset and read audio files
dataset = load_dataset("anton-l/superb_demo", "si", split="test")
dataset = dataset.map(map_to_array)

model = HubertForSequenceClassification.from_pretrained("superb/hubert-base-superb-sid")
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("superb/hubert-base-superb-sid")

# compute attention masks and normalize the waveform if needed
inputs = feature_extractor(dataset[:2]["speech"], sampling_rate=16000, padding=True, return_tensors="pt")

logits = model(**inputs).logits
predicted_ids = torch.argmax(logits, dim=-1)
labels = [model.config.id2label[_id] for _id in predicted_ids.tolist()]

📚 Documentation

Model description

This is a ported version of S3PRL's Hubert for the SUPERB Speaker Identification task.

The base model is hubert-base-ls960, which is pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.

For more information refer to SUPERB: Speech processing Universal PERformance Benchmark

Task and dataset description

Speaker Identification (SI) classifies each utterance for its speaker identity as a multi-class classification, where speakers are in the same predefined set for both training and testing. The widely used VoxCeleb1 dataset is adopted

For the original model's training and evaluation instructions refer to the S3PRL downstream task README.

Eval results

The evaluation metric is accuracy.

BibTeX entry and citation info

@article{yang2021superb,
  title={SUPERB: Speech processing Universal PERformance Benchmark},
  author={Yang, Shu-wen and Chi, Po-Han and Chuang, Yung-Sung and Lai, Cheng-I Jeff and Lakhotia, Kushal and Lin, Yist Y and Liu, Andy T and Shi, Jiatong and Chang, Xuankai and Lin, Guan-Ting and others},
  journal={arXiv preprint arXiv:2105.01051},
  year={2021}
}

🔧 Technical Details

The original document does not provide technical details, so this section is skipped.

📄 License

This project is licensed under the Apache 2.0 license.