# PreTrain Wav2Vec2 in Turkish

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-turkish%2F7848%3E%5C
**Category:** Flax/JAX Projects\
**Created:** [July 1, 2021, 2:56pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-turkish%2F7848 "2021-07-01T14:56:00Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![ceyda](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ceyda/32/3722_2.png) [@ceyda](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fceyda)%5C
**Post date:** [July 1, 2021, 2:56pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-turkish%2F7848%2F1 "2021-07-01T14:56:00Z")

</div>

# PreTrain Wav2Vec2 in Turkish

On the previous community event I pretrained a [Turkish Wav2Vec2 model](https://huggingface.co/ceyda/wav2vec2-base-760) using the fairseq script. This is a subpar model because I hadn’t cleaned the data.  
This time I want to do it properly with the freshly merged 🤗[FlaxWav2Vec2 + PreTraining script](https://github.com/huggingface/transformers/tree/master/examples/research_projects/jax-projects/wav2vec2)

## Model

A randomly initialized Wav2Vec2 model

## Datasets

One can make use [Common Voice](https://commonvoice.mozilla.org/en/languages) the dataset is also available through the `datasets` library here: [common\_voice · Datasets at Hugging Face](https://huggingface.co/datasets/common_voice).

## Available training scripts

FlaxWav2Vec2 will be merged soon: [[Flax] Add wav2vec2 by patrickvonplaten · Pull Request #12271 · huggingface/transformers · GitHub ](https://github.com/huggingface/transformers/pull/12271) and a pretraining script should be relatively easy to be merged.

## (Optional) Desired project outcome

The best Turkish ASR model.

## (Optional) Challenges

I have some additional scraped audiobook data. Might need a bit more though.

---

<div class="post-metadata">

**Author:** ![patrickvonplaten](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/patrickvonplaten/32/2171_2.png) [@patrickvonplaten](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpatrickvonplaten)%5C
**Post date:** [July 2, 2021, 3:32pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpretrain-wav2vec2-in-turkish%2F7848%2F2 "2021-07-02T15:32:47Z")

</div>

This is a well-defined topic, let’s define it as well!