Viwav2vec2 Base 3k

🚀 Wav2Vec2 base model trained of 3K hours of Vietnamese speech

This base model is pre - trained on Vietnamese speech audio, aiming to facilitate speech - related tasks such as automatic speech recognition.

🚀 Quick Start

The base model is pre - trained on 16kHz sampled speech audio from Vietnamese speech corpus containing 3K hours of spontaneous, reading, and broadcasting speech. When using the model, make sure that your speech input is also sampled at 16Khz. Note that this model should be fine - tuned on a downstream task, like Vietnamese Automatic Speech Recognition.

⚠️ Important Note

This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model for speech recognition, a tokenizer should be created and the model should be fine - tuned on labeled text data. Check out [this blog](https://huggingface.co/blog/fine - tune - wav2vec2 - english) for more in - detail explanation of how to fine - tune the model.

💻 Usage Examples

Basic Usage

import torch
from transformers import Wav2Vec2Model

model = Wav2Vec2Model.from_pretrained("dragonSwing/viwav2vec2-base-3k")

# Sanity check
inputs = torch.rand([1, 16000])
outputs = model(inputs)

Advanced Usage

See [this notebook](https://colab.research.google.com/drive/1FjTsqbYKphl9kL - eILgUc - bl4zVThL8F?usp=sharing) for more information on how to fine - tune the English pre - trained model.

📄 License

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

🔗 References

• [Facebook's Wav2Vec2 blog](https://ai.facebook.com/blog/wav2vec - 20 - learning - the - structure - of - speech - from - raw - audio/)
• Paper