# Audio Embedding with data2vec

*author: David Wang*


<br />



## Description

This operator extracts features for audio with [data2vec](https://arxiv.org/abs/2202.03555). 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.

<br />


## Code Example

Generate embeddings for the audio "test.wav".

*Write a pipeline with explicit inputs/outputs name specifications:*

```python
from towhee import pipe, ops, DataCollection

p = (
    pipe.input('path')
        .map('path', 'frame', ops.audio_decode.ffmpeg(sample_rate=16000))
        .map('frame', 'vecs', ops.audio_embedding.data2vec(model_name='facebook/data2vec-audio-base-960h'))
        .output('path', 'vecs')
)

DataCollection(p('test.wav')).show()
```

<img src="./result.png" width="800px"/>

<br />



## Factory Constructor

Create the operator via the following factory method

***data2vec(model_name='facebook/data2vec-audio-base')***

**Parameters:**


​  ***model_name***: *str*

The model name in string.
The default value is "facebook/data2vec-audio-base-960h".

Supported model name:
-
- facebook/data2vec-audio-base-960h
- facebook/data2vec-audio-large-960h
- facebook/data2vec-audio-base
- facebook/data2vec-audio-base-100h
- facebook/data2vec-audio-base-10m
- facebook/data2vec-audio-large
- facebook/data2vec-audio-large-100h
- facebook/data2vec-audio-large-10m

<br />



## Interface

An audio embedding operator generates vectors in numpy.ndarray given an audio file path or towhee audio frames.


**Parameters:**

​	***data:*** *List[towhee.types.audio_frame.AudioFrame]*

​	Input audio data is a list of towhee audio frames. The input data should represent for an audio longer than 0.9s.

**Returns:** *numpy.ndarray*

​   The audio embedding extracted by model.