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 .
The
Documentation and
Implementation of ChunkFormer are publicly available.
Public Models :
| STT | Model | #Params | Vivos | Common Voice | VLSP - Task 1 | Avg. |
|-----|------------------------------------------------------------------------|---------|-------|--------------|---------------|------|
| 1 |
ChunkFormer | 110M | 4.18 | 6.66 | 14.09 |
8.31 |
| 2 |
vinai/PhoWhisper-large | 1.55B | 4.67 | 8.14 | 13.75 | 8.85 |
| 3 |
nguyenvulebinh/wav2vec2-base-vietnamese-250h | 95M | 10.77 | 18.34 | 13.33 | 14.15 |
| 4 |
openai/whisper-large-v3 | 1.55B | 8.81 | 15.45 | 20.41 | 14.89 |
| 5 |
khanhld/wav2vec2-base-vietnamese-160h | 95M | 15.05 | 10.78 | 31.62 | 19.16 |
| 6 |
homebrewltd/Ichigo-whisper-v0.1 | 22M | 13.46 | 23.52 | 21.64 | 19.54 |
Private Models (API) :
| STT | Model | VLSP - Task 1 |
|-----|--------|---------------|
| 1 | ChunkFormer | 14.1 |
| 2 | Viettel | 14.5 |
| 3 | Google | 19.5 |
| 4 | FPT | 28.8 |
To use the ChunkFormer model for Vietnamese Automatic Speech Recognition, follow these steps:
1 git clone https://github.com/khanld/chunkformer.git
2 cd chunkformer
3 pip install -r requirements.txt
1 pip install huggingface_hub
2 huggingface-cli download khanhld/chunkformer-large-vie --local-dir "./chunkformer-large-vie"
1 git lfs install
2 git clone https://huggingface.co/khanhld/chunkformer-large-vie
This will download the model checkpoint to the checkpoints folder inside your chunkformer directory.
1 python decode.py \
2 --model_checkpoint path/to/local/chunkformer-large-vie \
3 --long_form_audio path/to/audio.wav \
4 --total_batch_duration 14400 \ #in second, default is 1800
5 --chunk_size 64 \
6 --left_context_size 128 \
7 --right_context_size 128
[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 audio1 @INPROCEEDINGS{10888640,
2 author={Le, Khanh and Ho, Tuan Vu and Tran, Dung and Chau, Duc Thanh},
3 booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
4 title={ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription},
5 year={2025},
6 volume={},
7 number={},
8 pages={1-5},
9 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},
10 doi={10.1109/ICASSP49660.2025.10888640}}
11 }
