huggingface / huggingface/blog

Unable to recreate Timit dataset results using wav2vec pretrained model

Open
#98 7 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
3.5k
Forks
1k
Avg merge
1d 20h
Merged PRs (30d)
19

Description

Hi,

I am unable to recreate the results reported in your blogpost https://huggingface.co/blog/fine-tune-wav2vec2-english on the timit dataset. I just ran the notebook as it is on google-colab, but got very different results. I am attaching a screenshot of the training and validation results. The results are completely different from the ones reported in the blog post. Can u please let m know the issue here? and how we can recreate the results?
Thanks
Screenshot 2021-04-07 at 8 05 37 PM

Contributor guide

No contributing guide indexed for this repository

Research direction

Open the linked wav2vec2 English fine-tuning blog notebook in Google Colab and compare its training and validation output with the attached screenshot. Determine why the TIMIT results diverge and document the steps or environment needed to reproduce the blog-post results.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
Domain
documentation, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.