Chunkformer Large Vie

🚀 ChunkFormer-Large-Vie: Large-Scale Pretrained ChunkFormer for Vietnamese Automatic Speech Recognition

ChunkFormer-Large-Vie is a large - scale Vietnamese Automatic Speech Recognition (ASR) model based on the ChunkFormer architecture, offering high - performance speech recognition for Vietnamese.

🚀 Quick Start

To use the ChunkFormer model for Vietnamese Automatic Speech Recognition, follow these steps:

1. Download the ChunkFormer Repository

git clone https://github.com/khanld/chunkformer.git
cd chunkformer
pip install -r requirements.txt   

2. Download the Model Checkpoint from Hugging Face

pip install huggingface_hub
huggingface-cli download khanhld/chunkformer-large-vie --local-dir "./chunkformer-large-vie"

or

git lfs install
git clone https://huggingface.co/khanhld/chunkformer-large-vie

This will download the model checkpoint to the checkpoints folder inside your chunkformer directory.

3. Run the model

python decode.py \
    --model_checkpoint path/to/local/chunkformer-large-vie \
    --long_form_audio path/to/audio.wav \
    --total_batch_duration 14400 \ #in second, default is 1800
    --chunk_size 64 \
    --left_context_size 128 \
    --right_context_size 128

Example Output:

[00:00:01.200] - [00:00:02.400]: this is a transcription example
[00:00:02.500] - [00:00:03.700]: testing the long-form audio

Advanced Usage can be found HERE

✨ Features

• High - performance ASR: Based on the ChunkFormer architecture, it provides accurate speech recognition for Vietnamese.
• Large - scale training: Fine - tuned on approximately 3000 hours of public Vietnamese speech data from diverse datasets.

📦 Installation

git clone https://github.com/khanld/chunkformer.git
cd chunkformer
pip install -r requirements.txt   

pip install huggingface_hub
huggingface-cli download khanhld/chunkformer-large-vie --local-dir "./chunkformer-large-vie"

or

git lfs install
git clone https://huggingface.co/khanhld/chunkformer-large-vie

💻 Usage Examples

Basic Usage

python decode.py \
    --model_checkpoint path/to/local/chunkformer-large-vie \
    --long_form_audio path/to/audio.wav \
    --total_batch_duration 14400 \ #in second, default is 1800
    --chunk_size 64 \
    --left_context_size 128 \
    --right_context_size 128

Advanced Usage

For advanced usage, please refer to HERE

📚 Documentation

The Documentation and Implementation of ChunkFormer are publicly available.

🔧 Technical Details

ChunkFormer-Large-Vie is a large-scale Vietnamese Automatic Speech Recognition (ASR) model based on the ChunkFormer architecture, introduced at ICASSP 2025. The model has been fine-tuned on approximately 3000 hours of public Vietnamese speech data sourced from diverse datasets. A list of datasets can be found HERE.

!!! Please note that only the [train-subset] was used for tuning the model.

We evaluate the models using Word Error Rate (WER). To ensure consistency and fairness in comparison, we manually apply Text Normalization, including the handling of numbers, uppercase letters, and punctuation.

📄 License

This project is licensed under the CC BY - NC 4.0 license.

📊 Benchmark Results

Public Models

Private Models (API)

📝 Citation

If you use this work in your research, please cite:

@INPROCEEDINGS{10888640,
  author={Le, Khanh and Ho, Tuan Vu and Tran, Dung and Chau, Duc Thanh},
  booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription}, 
  year={2025},
  volume={},
  number={},
  pages={1-5},
  keywords={Scalability;Memory management;Graphics processing units;Signal processing;Performance gain;Hardware;Resource management;Speech processing;Standards;Context modeling;chunkformer;masked batch;long-form transcription},
  doi={10.1109/ICASSP49660.2025.10888640}}
}

📞 Contact

• khanhld218@gmail.com
• 
• 

📋 Information Table