Wav2vec2 Xls R 300m Korean

🚀 Wav2Vec2 XLS-R 300M Korean

Wav2Vec2 XLS-R 300M Korean is an automatic speech recognition model based on the XLS-R architecture. It fine - tunes Wav2Vec2 - XLS - R - 300M on the Zeroth Korean dataset, offering a solution for Korean automatic speech recognition tasks.

🚀 Quick Start

This model is trained using HuggingFace's PyTorch framework and is part of the Robust Speech Challenge Event organized by HuggingFace. All training was done on a Tesla V100, sponsored by OVH. All necessary scripts used for training could be found in the Files and versions tab, as well as the Training metrics logged via Tensorboard.

✨ Features

• Based on the advanced XLS - R architecture, suitable for automatic speech recognition tasks.
• Fine - tuned on the Zeroth Korean dataset, optimized for the Korean language.

📦 Installation

No installation steps were provided in the original README.

💻 Usage Examples

No code examples were provided in the original README.

📚 Documentation

Model

Evaluation Results

The model achieves the following results on evaluation:

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 7.5e - 05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9, 0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 50.0
• mixed_precision_training: Native AMP

Training results

Disclaimer

⚠️ Important Note

Do consider the biases which came from pre - training datasets that may be carried over into the results of this model.

Authors

Wav2Vec2 XLS - R 300M Korean was trained and evaluated by Wilson Wongso. All computation and development are done on OVH Cloud.

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.2.dev0
• Tokenizers 0.10.3

📄 License

This model is licensed under the Apache 2.0 license.