Upload 11 files

.gitattributes

@@ -1,35 +1,36 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+paper.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,195 @@
+---
+language: vie
+datasets:
+- legacy-datasets/common_voice
+- vlsp2020_vinai_100h
+- AILAB-VNUHCM/vivos
+- doof-ferb/vlsp2020_vinai_100h
+- doof-ferb/fpt_fosd
+- doof-ferb/infore1_25hours
+- linhtran92/viet_bud500
+- doof-ferb/LSVSC
+- doof-ferb/vais1000
+- doof-ferb/VietMed_labeled
+- NhutP/VSV-1100
+- doof-ferb/Speech-MASSIVE_vie
+- doof-ferb/BibleMMS_vie
+- capleaf/viVoice
+metrics:
+- wer
+pipeline_tag: automatic-speech-recognition
+tags:
+- transcription
+- audio
+- speech
+- chunkformer
+- asr
+- automatic-speech-recognition
+license: cc-by-nc-4.0
+model-index:
+- name: ChunkFormer Large Vietnamese
+  results:
+  - task:
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common-voice-vietnamese
+      type: common_voice
+      args: vi
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 6.66
+    source:
+      name: Common Voice Vi Leaderboard
+      url: https://paperswithcode.com/sota/speech-recognition-on-common-voice-vi
+  - task:
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: VIVOS
+      type: vivos
+      args: vi
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 4.18
+    source:
+      name: Vivos Leaderboard
+      url: https://paperswithcode.com/sota/speech-recognition-on-vivos
+  - task:
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: VLSP - Task 1
+      type: vlsp
+      args: vi
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 14.09
+---
+
+# **ChunkFormer-Large-Vie: Large-Scale Pretrained ChunkFormer for Vietnamese Automatic Speech Recognition**
+<style>
+img {
+ display: inline;
+}
+</style>
+[![Ranked #1: Speech Recognition on Common Voice Vi](https://img.shields.io/badge/Ranked%20%231%3A%20Speech%20Recognition%20on%20Common%20Voice%20Vi-%F0%9F%8F%86%20SOTA-blueviolet?style=for-the-badge&logo=paperswithcode&logoColor=white)](https://paperswithcode.com/sota/speech-recognition-on-common-voice-vi)
+[![Ranked #1: Speech Recognition on VIVOS](https://img.shields.io/badge/Ranked%20%231%3A%20Speech%20Recognition%20on%20VIVOS-%F0%9F%8F%86%20SOTA-blueviolet?style=for-the-badge&logo=paperswithcode&logoColor=white)](https://paperswithcode.com/sota/speech-recognition-on-vivos)
+
+[![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc/4.0/) 
+[![GitHub](https://img.shields.io/badge/GitHub-ChunkFormer-blue)](https://github.com/khanld/chunkformer)
+[![Paper](https://img.shields.io/badge/Paper-ICASSP%202025-green)](https://arxiv.org/abs/2502.14673)
+[![Model size](https://img.shields.io/badge/Params-110M-lightgrey#model-badge)](#description)
+
+---
+## Table of contents
+1. [Model Description](#description)
+2. [Documentation and Implementation](#implementation)
+3. [Benchmark Results](#benchmark)
+4. [Usage](#usage)
+6. [Citation](#citation)
+7. [Contact](#contact)
+
+---
+<a name = "description" ></a>
+## Model Description
+**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**](dataset.tsv). 
+
+**!!! Please note that only the \[train-subset\] was used for tuning the model.**
+
+---
+<a name = "implementation" ></a>
+## Documentation and Implementation
+The [Documentation]() and [Implementation](https://github.com/khanld/chunkformer) of ChunkFormer are publicly available.
+
+---
+<a name = "benchmark" ></a>
+## Benchmark Results
+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.
+
+1. **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](https://huggingface.co/vinai/PhoWhisper-large)  | 1.55B   | 4.67  | 8.14         | 13.75         | 8.85 |
+| 3   | [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) | 95M     | 10.77 | 18.34        | 13.33         | 14.15 |
+| 4   | [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 1.55B   | 8.81     | 15.45            | 20.41          | 14.89    |
+| 5   | [khanhld/wav2vec2-base-vietnamese-160h](https://huggingface.co/khanhld/wav2vec2-base-vietnamese-160h) | 95M     | 15.05 | 10.78        | 31.62             | 19.16    |
+| 6   | [homebrewltd/Ichigo-whisper-v0.1](https://huggingface.co/homebrewltd/Ichigo-whisper-v0.1) | 22M   | 13.46     | 23.52            | 21.64          | 19.54    |
+
+2. **Private Models (API)**:
+| STT | Model  | VLSP - Task 1 |
+|-----|--------|---------------|
+| 1   | **ChunkFormer** | **14.1**             |
+| 2   | Viettel     | 14.5          |
+| 3   | Google  | 19.5          |
+| 4   | FPT   | 28.8          |
+
+---
+<a name = "usage" ></a>
+## Quick Usage
+To use the ChunkFormer model for Vietnamese Automatic Speech Recognition, follow these steps:
+
+1. **Download the ChunkFormer Repository**
+```bash
+git clone https://github.com/khanld/chunkformer.git
+cd chunkformer
+pip install -r requirements.txt   
+```
+2. **Download the Model Checkpoint from Hugging Face**
+```bash
+pip install huggingface_hub
+huggingface-cli download khanhld/chunkformer-large-vie --local-dir "./chunkformer-large-vie"
+```
+or
+```bash
+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**
+```bash
+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](https://github.com/khanld/chunkformer/tree/main?tab=readme-ov-file#usage)
+
+---
+<a name = "citation" ></a>
+## Citation
+If you use this work in your research, please cite:
+
+```bibtex
+@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}}
+}
+```
+
+---
+<a name = "contact"></a>
+## Contact
+- [email protected]
+- [![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/khanld)
+- [![LinkedIn](https://img.shields.io/badge/linkedin-%230077B5.svg?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/khanhld257/)

config.yaml

@@ -0,0 +1,33 @@
+encoder: chunkformer
+is_json_cmvn: true
+cmvn_file: chunkformer-large-vie/global_cmvn
+input_dim: 80
+output_dim: 6992
+
+encoder_conf:
+    output_size: 512    # dimension of attention
+    attention_heads: 8
+    linear_units: 2048  # the number of units of position-wise feed forward
+    num_blocks: 17      # the number of encoder blocks
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: 'depthwise' # encoder input type, you can chose conv2d, conv2d6 and conv2d8
+    normalize_before: true
+    cnn_module_kernel: 15
+    use_cnn_module: true
+    activation_type: 'swish'
+    pos_enc_layer_type: 'stream_rel_pos'
+    selfattention_layer_type: 'stream_rel_selfattn'
+    causal: false
+    use_dynamic_chunk: false
+    use_limited_chunk: false
+    use_context_hint_chunk: false
+    right_context_probs: [0.75]
+    right_context_sizes: [128, 128, 128]
+    limited_decoding_chunk_sizes: [64, 128, 256]
+    limited_left_chunk_sizes: [128, 256, 128]
+    cnn_module_norm: 'layer_norm' # using nn.LayerNorm makes model converge faster
+    use_dynamic_left_chunk: false
+    use_dynamic_conv: true
+    freeze_subsampling_layer: false

dataset.tsv

@@ -0,0 +1,15 @@
+		
+data	Estimated hour	Link
+AILAB-VNUHCM/vivos	15	https://huggingface.co/datasets/AILAB-VNUHCM/vivos
+doof-ferb/vlsp2020_vinai_100h	100	https://huggingface.co/datasets/doof-ferb/vlsp2020_vinai_100h
+doof-ferb/fpt_fosd	100	https://huggingface.co/datasets/doof-ferb/fpt_fosd
+doof-ferb/infore1_25hours	25	https://huggingface.co/datasets/doof-ferb/infore1_25hours
+linhtran92/viet_bud500	500	https://huggingface.co/datasets/linhtran92/viet_bud500
+doof-ferb/LSVSC	100	https://huggingface.co/datasets/doof-ferb/LSVSC
+doof-ferb/vais1000	2	https://huggingface.co/datasets/doof-ferb/vais1000
+doof-ferb/VietMed_labeled	3	https://huggingface.co/datasets/doof-ferb/VietMed_labeled
+NhutP/VSV-1100	1100	https://huggingface.co/datasets/NhutP/VSV-1100
+doof-ferb/Speech-MASSIVE_vie	1	https://huggingface.co/datasets/doof-ferb/Speech-MASSIVE_vie
+doof-ferb/BibleMMS_vie	1	https://huggingface.co/datasets/doof-ferb/BibleMMS_vie
+capleaf/viVoice	1000	https://huggingface.co/datasets/capleaf/viVoice
+linhtran92/viet_youtube_asr_corpus_v2	100	https://huggingface.co/datasets/linhtran92/viet_youtube_asr_corpus_v2

global_cmvn

@@ -0,0 +1 @@
+{"mean_stat": [11719716864.0, 12109591552.0, 13372244992.0, 14431860736.0, 15379044352.0, 16048251904.0, 16420151296.0, 16462806016.0, 16435909632.0, 16277902336.0, 16328012800.0, 16365081600.0, 16567385088.0, 16710700032.0, 16709065728.0, 16702018560.0, 16609516544.0, 16454155264.0, 16481000448.0, 16182266880.0, 15951698944.0, 16123002880.0, 15874306048.0, 15979340800.0, 15849950208.0, 15899969536.0, 15757883392.0, 15813523456.0, 15752173568.0, 15734062080.0, 15719752704.0, 15666200576.0, 15647021056.0, 15673847808.0, 15692921856.0, 15761361920.0, 15846681600.0, 15889658880.0, 15914716160.0, 15815398400.0, 15872250880.0, 15785680896.0, 15849245696.0, 15839742976.0, 15926661120.0, 16051468288.0, 16199239680.0, 16324781056.0, 16408131584.0, 16480964608.0, 16454390784.0, 16394480640.0, 16379509760.0, 16433426432.0, 16476341248.0, 16498354176.0, 16476703744.0, 16432917504.0, 16377098240.0, 16309888000.0, 16293634048.0, 16223672320.0, 16094388224.0, 15930726400.0, 15795167232.0, 15654544384.0, 15517620224.0, 15460015104.0, 15418070016.0, 15386569728.0, 15329652736.0, 15294281728.0, 15287447552.0, 15333227520.0, 15422593024.0, 15514677248.0, 15527650304.0, 15340513280.0, 14994009088.0, 14165908480.0], "var_stat": [150319136768.0, 161704574976.0, 194916073472.0, 223425839104.0, 250741407744.0, 271204204544.0, 283238137856.0, 285300719616.0, 283947597824.0, 278054535168.0, 279273865216.0, 280822546432.0, 287651364864.0, 292578492416.0, 292665622528.0, 292221845504.0, 288983515136.0, 283743879168.0, 284274917376.0, 274934988800.0, 267933974528.0, 272869457920.0, 265080864768.0, 267923013632.0, 263733788672.0, 265018474496.0, 260564975616.0, 262147883008.0, 260146626560.0, 259420569600.0, 258994372608.0, 257408565248.0, 256659259392.0, 257174503424.0, 257758822400.0, 259958472704.0, 262545031168.0, 263766671360.0, 264487256064.0, 261593858048.0, 263239712768.0, 260605640704.0, 262439223296.0, 262260129792.0, 264741273600.0, 268570198016.0, 273416044544.0, 277515993088.0, 280181997568.0, 282168197120.0, 280982159360.0, 279186898944.0, 278822191104.0, 280607490048.0, 282087915520.0, 282732265472.0, 281854050304.0, 280297209856.0, 278515056640.0, 276357185536.0, 275706642432.0, 273547116544.0, 269666041856.0, 264639021056.0, 260329226240.0, 256096075776.0, 252133769216.0, 250319650816.0, 249039454208.0, 247930339328.0, 246243737600.0, 245079801856.0, 244788805632.0, 246247636992.0, 248876138496.0, 251564457984.0, 251790016512.0, 246503702528.0, 236531630080.0, 212810301440.0], "frame_num": 1074281799}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95394958efbb22d9bf22b027f1867d7b04aa803b09ec82d1e5bd67a40f7ea6c8
+size 613743208

paper.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c63fd1e0799d7095603e6cfce0db0b17a75673249d1558033f70630cb948db
+size 799967

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c9d6e0dab607655c8babb01718066f6e08ccc8e6419acc1a67df971ad7ee99
+size 613951335