# Audio Embdding 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 the pipeline in simplified style*:

```python
import towhee

(
    towhee.glob('test.wav')
          .audio_decode.ffmpeg()
          .runas_op(func=lambda x:[y[0] for y in x])
          .towhee.data2vec_audio()
          .show()
)

```
<img src="https://towhee.io/towhee/data2vec-vision/raw/branch/main/result1.png" alt="result1" style="height:20px;"/>

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

```python
import towhee

(
    towhee.glob['path']('test.wav')
          .audio_decode.ffmpeg['path', 'frames']()
          .runas_op['frames', 'frames'](func=lambda x:[y[0] for y in x])
          .towhee.data2vec_audio['frames', 'vecs'](model_name="facebook/data2vec-audio-base-960h") 
          .show()
)
```
<img src="https://towhee.io/towhee/data2vec-vision/raw/branch/main/result2.png" alt="result2" style="height:60px;"/>


<br />



## Factory Constructor

Create the operator via the following factory method

***data2vec_vision(model_name='facebook/data2vec-vision-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.