kushinada-hubert-large Open-Source Model - Free for Japanese Speech Feature Extraction

Kushinada Hubert Large

Developed by imprt

A Japanese HuBERT Large model pre-trained on 62,215 hours of Japanese TV broadcast audio data for speech feature extraction

Speech Recognition

PyTorch

JapaneseOpen Source License:Apache-2.0 #Japanese speech feature extraction #Large-scale pre-training #TV broadcast audio

Downloads 1,041

Release Time : 3/7/2025

Model Overview

This is a pre-trained model specifically designed for Japanese speech feature extraction, trained on a large amount of Japanese TV broadcast audio data, suitable for speech processing tasks

Model Features

Large-scale Japanese data training

Pre-trained on 62,215 hours of Japanese TV broadcast audio data

HuBERT Large architecture

Utilizes the high-performance HuBERT Large model architecture

Professional speech feature extraction

Specifically designed feature extraction capabilities for speech signals

Model Capabilities

Speech feature extraction

Japanese speech processing

Use Cases

Speech processing

Speech recognition preprocessing

Provides high-quality feature inputs for Japanese speech recognition systems

Speech analysis

Extracts speech features for tasks such as emotion analysis and speaker recognition

🚀 `imprt/kushinada-hubert-large`

This is a Japanese HuBERT Large model for feature extraction. It was pre - trained on 62,215 hours of audio from large - scale Japanese TV broadcasts, and the training used code from the official repository.

🚀 Quick Start

Before downloading this model, please read the Apache License, Version 2.0. You need to acknowledge some information:

Country: Enter your country.
Affiliation: Provide relevant text information.
I agree ALL the statements in Apache License, Version 2: Check this checkbox to indicate your agreement.

Click the "Acknowledge license" button to proceed.

✨ Features

This is a Japanese HuBERT Large model pre - trained using 62215 hours of audio. The audio was extracted from large - scale Japanese TV broadcast audio data by voice activity detection. The model was trained using code from the official repository.

💻 Usage Examples

Basic Usage

import soundfile as sf
from transformers import AutoFeatureExtractor
model = "imprt/kushinada-hubert-large"
feature_extractor = AutoFeatureExtractor.from_pretrained(model)
audio_file="/path/to/16k_audio_file"
audio_input, sr = sf.read(audio_file)
feature_extractor(audio_input, sampling_rate=sr)

📚 Documentation

References

@article{journals/corr/abs-2106-07447,
  added-at = {2021-06-16T00:00:00.000+0200},
  author = {Hsu, Wei-Ning and Bolte, Benjamin and Tsai, Yao-Hung Hubert and Lakhotia, Kushal and Salakhutdinov, Ruslan and Mohamed, Abdelrahman},
  biburl = {https://www.bibsonomy.org/bibtex/2435bd8c9ac37a4eab204ded15e9f8918/dblp},
  ee = {https://arxiv.org/abs/2106.07447},
  interhash = {c85407653eddc9c9256c261afe8d6954},
  intrahash = {435bd8c9ac37a4eab204ded15e9f8918},
  journal = {CoRR},
  keywords = {dblp},
  timestamp = {2024-04-08T22:55:35.000+0200},
  title = {HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units.},
  url = {http://dblp.uni-trier.de/db/journals/corr/corr2106.html#abs-2106-07447},
  volume = {abs/2106.07447},
  year = 2021
}

📄 License

This model is released under the Apache License, Version 2.0.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご