# Is there any tutorial 4 pretrain wav2vec2

**URL:** <https://discuss.huggingface.co/t/is-there-any-tutorial-4-pretrain-wav2vec2/11718>\
**Category:** Beginners\
**Created:** [November 15, 2021, 9:47am UTC](https://discuss.huggingface.co/t/is-there-any-tutorial-4-pretrain-wav2vec2/11718 "2021-11-15T09:47:36Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Eilander](https://avatars.discourse-cdn.com/v4/letter/e/a4c791/32.png) [@Eilander](https://discuss.huggingface.co/u/Eilander)\
**Post date:** [November 15, 2021, 9:47am UTC](https://discuss.huggingface.co/t/is-there-any-tutorial-4-pretrain-wav2vec2/11718/1 "2021-11-15T09:47:36Z")

</div>

Hi, guys!

I was trying to pretrain a wav2vec2 from scratch. However, the loss is continuous remains high and is never reduced.

So I wonder if there is a tutorial for pretrain wav2vec2. Looking forward to your reply.

Regard,  
Eilander

---

<div class="post-metadata">

**Author:** ![Kshitizkhandelwal](https://avatars.discourse-cdn.com/v4/letter/k/c68b51/32.png) [@Kshitizkhandelwal](https://discuss.huggingface.co/u/Kshitizkhandelwal)\
**Post date:** [November 14, 2022, 1:09pm UTC](https://discuss.huggingface.co/t/is-there-any-tutorial-4-pretrain-wav2vec2/11718/2 "2022-11-14T13:09:07Z")

</div>

@Eilander did you find any solution to this problem? If you have pre trained a model can you please share the code

---

<div class="post-metadata">

**Author:** ![sanchit-gandhi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sanchit-gandhi/32/21280_2.png) [@sanchit-gandhi](https://discuss.huggingface.co/u/sanchit-gandhi)\
**Post date:** [November 14, 2022, 5:36pm UTC](https://discuss.huggingface.co/t/is-there-any-tutorial-4-pretrain-wav2vec2/11718/3 "2022-11-14T17:36:13Z")

</div>

Have you checked out the README here? [transformers/examples/pytorch/speech-pretraining at main · huggingface/transformers · GitHub](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-pretraining#speech-recognition-pre-training)

---

<div class="post-metadata">

**Author:** ![bilalhsp](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/bilalhsp/32/34048_2.png) [@bilalhsp](https://discuss.huggingface.co/u/bilalhsp)\
**Post date:** [November 5, 2024, 8:07pm UTC](https://discuss.huggingface.co/t/is-there-any-tutorial-4-pretrain-wav2vec2/11718/4 "2024-11-05T20:07:06Z")

</div>

Hi @Eilander did you find what you were looking for? If not, this tutorial might be helpful for you;

> **[Pretraining wav2vec2 using Huggingface Trainer API](https://medium.com/@bilalhsp/pretraining-wav2vec2-using-huggingface-trainer-api-19fbf2fc6bf2)**
>
> Self-supervised training using audio data.

---

<div class="post-metadata">

**Author:** ![benstokes](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/benstokes/32/32007_2.png) [@benstokes](https://discuss.huggingface.co/u/benstokes)\
**Post date:** [November 6, 2024, 1:45am UTC](https://discuss.huggingface.co/t/is-there-any-tutorial-4-pretrain-wav2vec2/11718/5 "2024-11-06T01:45:49Z")

</div>

> [@sanchit-gandhi](#):
>
> Have you checked out the README here? [transformers/examples/pytorch/speech-pretraining at main · huggingface/transformers · GitHub](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-pretraining#speech-recognition-pre-training) [applebees happy](https://applebeeshappyhours.us/)

Thanks for sharing amazing tutorial. I face difficulties to find this topic. Thanks