Data2vec Audio Base 100h

🚀 Data2Vec-Audio-Base-100h

A pre - trained and fine - tuned base model on 100 hours of Librispeech for 16kHz sampled speech audio.

This model is the base model that has been pre - trained and fine - tuned on 100 hours of Librispeech with 16kHz sampled speech audio. When using the model, ensure that your speech input is also sampled at 16kHz.

🚀 Quick Start

Model Information

• Model Link: Facebook's Data2Vec
• Paper: Paper
• Authors: Alexei Baevski, Wei - Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, Michael Auli

Abstract

While the general idea of self - supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self - supervised learning, we present data2vec, a framework that uses the same learning method for either speech, NLP or computer vision. The core idea is to predict latent representations of the full input data based on a masked view of the input in a self - distillation setup using a standard Transformer architecture. Instead of predicting modality - specific targets such as words, visual tokens or units of human speech which are local in nature, data2vec predicts contextualized latent representations that contain information from the entire input. Experiments on the major benchmarks of speech recognition, image classification, and natural language understanding demonstrate a new state of the art or competitive performance to predominant approaches.

The original model can be found under https://github.com/pytorch/fairseq/tree/main/examples/data2vec.

✨ Features

• Multimodal Applicability: Uses the same learning method for speech, NLP, and computer vision.
• Contextualized Prediction: Predicts contextualized latent representations containing information from the entire input.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

To transcribe audio files, the model can be used as a standalone acoustic model as follows:

from transformers import Wav2Vec2Processor, Data2VecForCTC
from datasets import load_dataset
import torch

# load model and processor
processor = Wav2Vec2Processor.from_pretrained("facebook/data2vec-audio-base-100h")
model = Data2VecForCTC.from_pretrained("facebook/data2vec-audio-base-100h")

# load dummy dataset and read soundfiles
ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")

# tokenize
input_values = processor(ds[0]["audio"]["array"], 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)

🔧 Technical Details

Pre - Training method

For more information, please take a look at the official paper.

📄 License

This project is licensed under the apache - 2.0 license.

📦 Information Table