license: cc-by-4.0 datasets:

• openslr/librispeech_asr language:
• en pipeline_tag: audio-to-audio

SSLZip

使用方法

import onnxruntime as ort
from transformers import HubertModel
import torch

# Load the upstream HuBERT model.
upstream = HubertModel.from_pretrained("facebook/hubert-base-ls960")
upstream.eval()

# Load the autoencoder model.
postprocessor = ort.InferenceSession("sslzip_256_club.onnx")
node_name = postprocessor.get_inputs()[0].name

# Prepare an input waveform (assuming 16kHz audio).
x = torch.randn(1, 16000)

# Extract the latent representation for downstream tasks.
with torch.inference_mode():
    h = upstream(x, output_hidden_states=True).hidden_states[-1]
    z = postprocessor.run(None, {node_name: h.cpu().numpy()})[0]

# Use z as you like.
print(z.shape)

许可证

该预训练模型使用 LibriSpeech 语料库开发，并在相同许可证（CC BY 4.0）下分发。
使用此模型时，请注明名古屋工业大学和 Techno-Speech, Inc. 的贡献。

引用

@InProceedings{yoshimura2025sslzip,
  author = {Takenori Yoshimura and Shinji Takaki and Kazuhiro Nakamura and Keiichiro Oura and Takato Fujimoto and Kei Hashimoto and Yoshihiko Nankaku and Keiichi Tokuda},
  title = {{SSLZip}: Simple autoencoding for enhancing self-supervised speech representations in speech generation},
  booktitle = {13th ISCA Speech Synthesis Workshop (SSW 2025)},
  pages = {xxx--xxx},
  year = {2025},
}