# Understanding Wav2vec2Processor

**URL:** <https://discuss.huggingface.co/t/understanding-wav2vec2processor/12804>\
**Category:** Beginners\
**Created:** [December 14, 2021, 12:23pm UTC](https://discuss.huggingface.co/t/understanding-wav2vec2processor/12804 "2021-12-14T12:23:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tzeviya](https://avatars.discourse-cdn.com/v4/letter/t/6a8cbe/32.png) [@tzeviya](https://discuss.huggingface.co/u/tzeviya)\
**Post date:** [December 14, 2021, 12:23pm UTC](https://discuss.huggingface.co/t/understanding-wav2vec2processor/12804/1 "2021-12-14T12:23:38Z")

</div>

Hi,

I’m trying to use wav2vec2 for its output feature vectors. My input is audio files, and I don’t want to use any information about its textual content.

This is the model I’m using:

`model = Wav2Vec2Model.from_pretrained('facebook/wav2vec2-base')`

It seems that a `feature extractor` should be defined as well:

`feature_extractor = Wav2Vec2Processor.from_pretrained('facebook/wav2vec2-base')`

Then, when training:

```auto
audio_file = feature_extractor(audio_file, return_tensors="pt", padding=True, feature_size=1, sampling_rate=16000 )
output = model(**audio_file)

```

What is the feature\_extractor needed for? Doesn’t the model itself include a feature extractor?