Hubert Base Korean

🚀 hubert-base-korean

Hubert-base-korean is a speech representation learning model designed for Korean automatic speech recognition. It uses self - supervised learning to train directly on raw audio waveforms, offering a new approach to speech recognition.

🚀 Quick Start

💻 Usage Examples

Basic Usage

# Pytorch example
import torch
from transformers import HubertModel

model = HubertModel.from_pretrained("team-lucid/hubert-base-korean")

wav = torch.ones(1, 16000)
outputs = model(wav)
print(f"Input:   {wav.shape}")  # [1, 16000]
print(f"Output:  {outputs.last_hidden_state.shape}")  # [1, 49, 768]

Advanced Usage

# JAX/Flax example
import jax.numpy as jnp
from transformers import FlaxAutoModel

model = FlaxAutoModel.from_pretrained("team-lucid/hubert-base-korean", trust_remote_code=True)

wav = jnp.ones((1, 16000))
outputs = model(wav)
print(f"Input:   {wav.shape}")  # [1, 16000]
print(f"Output:  {outputs.last_hidden_state.shape}")  # [1, 49, 768]

✨ Features

Hubert (Hidden-Unit BERT) is a speech representation learning model proposed by Facebook. Unlike traditional speech recognition models, Hubert uses a self - supervised learning approach that directly learns from the raw waveform of speech signals. This research was trained on a Cloud TPU supported by Google's TPU Research Cloud (TRC).

Model Description

🔧 Technical Details

Training Data

This model was trained on approximately 4,000 hours of data extracted from Free Conversation Speech (General Male and Female), Multi - Speaker Speech Synthesis Data, and Broadcast Content Dialogue - Style Speech Recognition Data, which were constructed with the support of the Institute for Information & communications Technology Planning & Evaluation under the Ministry of Science and ICT.

Training Procedure

Similar to the original paper, the Base model was first trained based on MFCC. Then, k - means clustering with 500 clusters was performed, and both the Base and Large models were retrained.

Training Hyperparameters

📄 License

This model is licensed under the Apache 2.0 license.