metadata

language: vi
datasets:
  - vlsp
  - vivos
tags:
  - audio
  - automatic-speech-recognition
license: cc-by-nc-4.0
widget:
  - label: VLSP ASR 2020 test T1
    src: >-
      https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h/raw/main/audio-test/t1_0001-00010.wav
  - label: VLSP ASR 2020 test T1
    src: >-
      https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h/raw/main/audio-test/t1_utt000000042.wav
  - label: VLSP ASR 2020 test T2
    src: >-
      https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h/raw/main/audio-test/t2_0000006682.wav
model-index:
  - name: Vietnamese end-to-end speech recognition using wav2vec 2.0 by VietAI
    results:
      - task:
          name: Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice vi
          type: common_voice
          args: vi
        metrics:
          - name: Test WER
            type: wer
            value: 11.52
      - task:
          name: Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: VIVOS
          type: vivos
          args: vi
        metrics:
          - name: Test WER
            type: wer
            value: 6.15

Vietnamese end-to-end speech recognition using wav2vec 2.0

Facebook's Wav2Vec2

Model description

Our models are pre-trained on 13k hours of Vietnamese youtube audio (un-label data) and fine-tuned on 250 hours labeled of VLSP ASR dataset on 16kHz sampled speech audio.

We use wav2vec2 architecture for the pre-trained model. Follow wav2vec2 paper:

For the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler.

For fine-tuning phase, wav2vec2 is fine-tuned using Connectionist Temporal Classification (CTC), which is an algorithm that is used to train neural networks for sequence-to-sequence problems and mainly in Automatic Speech Recognition and handwriting recognition.

Model	#params	Pre-training data	Fine-tune data
base	95M	13k hours	250 hours

In a formal ASR system, two components are required: acoustic model and language model. Here ctc-wav2vec fine-tuned model works as an acoustic model. For the language model, we provide a 4-grams model trained on 2GB of spoken text.

Detail of training and fine-tuning process, the audience can follow fairseq github and huggingface blog.

Benchmark WER result:

	VIVOS	COMMON VOICE VI	VLSP-T1	VLSP-T2
without LM	10.77	18.34	13.33	51.45
with 4-grams LM	6.15	11.52	9.11	40.81

Example usage

When using the model make sure that your speech input is sampled at 16Khz. Audio length should be shorter than 10s. Following the Colab link below to use a combination of CTC-wav2vec and 4-grams LM.

from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
from datasets import load_dataset
import soundfile as sf
import torch

# load model and tokenizer
processor = Wav2Vec2Processor.from_pretrained("nguyenvulebinh/wav2vec2-base-vietnamese-250h")
model = Wav2Vec2ForCTC.from_pretrained("nguyenvulebinh/wav2vec2-base-vietnamese-250h")

# define function to read in sound file
def map_to_array(batch):
    speech, _ = sf.read(batch["file"])
    batch["speech"] = speech
    return batch

# load dummy dataset and read soundfiles
ds = map_to_array({
    "file": 'audio-test/t1_0001-00010.wav'
})

# tokenize
input_values = processor(ds["speech"], return_tensors="pt", padding="longest").input_values  # Batch size 1

# retrieve logits
logits = model(input_values).logits

# take argmax and decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)

Model Parameters License

The ASR model parameters are made available for non-commercial use only, under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. You can find details at: https://creativecommons.org/licenses/by-nc/4.0/legalcode

Citation

@misc{Thai_Binh_Nguyen_wav2vec2_vi_2021,
  author = {Thai Binh Nguyen},
  doi = {10.5281/zenodo.5356039},
  month = {09},
  title = {{Vietnamese end-to-end speech recognition using wav2vec 2.0}},
  url = {https://github.com/vietai/ASR},
  year = {2021}
}

Please CITE our repo when it is used to help produce published results or is incorporated into other software.

Contact

[email protected] / [email protected]