Hubert-Large语音说话人识别模型

模型描述

这是 S3PRL's Hubert for the SUPERB Speaker Identification task 的移植版本。

基础模型是 hubert-large-ll60k ，它是在16kHz采样的语音音频上进行预训练的。在使用模型时，请确保语音输入也以16kHz采样。

有关更多信息，请参考 SUPERB: Speech processing Universal PERformance Benchmark 。

任务与数据集说明

说话人识别（SI）将每个话语分类为其说话人身份，作为一种多类分类，其中训练和测试中的说话人均属于同一预定义集合。采用了广泛使用的 VoxCeleb1 数据集。

有关原始模型的训练和评估说明，请参考 S3PRL downstream task README 。

用法示例

您可以通过音频分类流程使用模型：

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-large-superb-sid")
labels = classifier(dataset[0]["file"], top_k=5)

或直接使用模型：

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-large-superb-sid")
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("superb/hubert-large-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()]

评估结果

评估指标为准确性。

BibTeX条目和引用信息

@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}
}