# Finetuning Wav2Vec2 for ASR notebook doesn't work

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuning-wav2vec2-for-asr-notebook-doesnt-work%2F22905%3E%5C
**Category:** 🤗Datasets\
**Created:** [September 9, 2022, 7:24pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuning-wav2vec2-for-asr-notebook-doesnt-work%2F22905 "2022-09-09T19:24:14Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Gozdi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/gozdi/32/4221_2.png) [@Gozdi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGozdi)%5C
**Post date:** [September 9, 2022, 7:24pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetuning-wav2vec2-for-asr-notebook-doesnt-work%2F22905%2F1 "2022-09-09T19:24:14Z")

</div>

Hi I was looking through colab notebook of this [blog post](https://huggingface.co/blog/fine-tune-wav2vec2-english) and I got this `RuntimeError: Error opening <fsspec.implementations.local.LocalFileOpener object at 0x7fd36e6e5dd0>: File contains data in an unknown format.` calling prepare\_dataset function  
It happens every time I try to call dataset object containing audio column. In the past calling `timit["train"][0]["audio"]` would return dictionary with array, sampling rate, and file path now it is this runtime error.  
What can I do about it??