# Using wav2vec2 for own usecase

**URL:** <https://discuss.huggingface.co/t/using-wav2vec2-for-own-usecase/6147>\
**Category:** Beginners\
**Created:** [May 12, 2021, 4:45pm UTC](https://discuss.huggingface.co/t/using-wav2vec2-for-own-usecase/6147 "2021-05-12T16:45:45Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ayushb](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ayushb/32/2954_2.png) [@Ayushb](https://discuss.huggingface.co/u/Ayushb)\
**Post date:** [May 12, 2021, 4:45pm UTC](https://discuss.huggingface.co/t/using-wav2vec2-for-own-usecase/6147/1 "2021-05-12T16:45:45Z")

</div>

I’m looking to use wav2vec2 english for own project use-case for the purpose of transcription, it is possible that I can feed large audio files (upto 1hr of duration) for the task?  
Thanks in Advance!

---

<div class="post-metadata">

**Author:** ![Rajaram1996](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/rajaram1996/32/3025_2.png) [@Rajaram1996](https://discuss.huggingface.co/u/Rajaram1996)\
**Post date:** [May 12, 2021, 7:34pm UTC](https://discuss.huggingface.co/t/using-wav2vec2-for-own-usecase/6147/2 "2021-05-12T19:34:48Z")

</div>

Yes, you should be able to. [Here](https://huggingface.co/blog/fine-tune-wav2vec2-english) are some references on fine-tuning wav2vec on common voice dataset. With a csv file having one column for location of audio clips and the other column the label, you can fine-tune it for your own audio files.

---

<div class="post-metadata">

**Author:** ![Ayushb](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ayushb/32/2954_2.png) [@Ayushb](https://discuss.huggingface.co/u/Ayushb)\
**Post date:** [May 13, 2021, 6:13am UTC](https://discuss.huggingface.co/t/using-wav2vec2-for-own-usecase/6147/4 "2021-05-13T06:13:52Z")

</div>

Thanks will definitely check this out!