[Speech Commands] Add notebook for training custom models in Python #506
Conversation
in Python, using a set of .wav files.
|
Check out this pull request on Review Jupyter notebook visual diffs & provide feedback on notebooks. Powered by ReviewNB |
caisq
changed the title
…sq/tfjs-models into sc-train-custom-audio-model-notebook
|
Gentle ping @pyu10055. Do you have time to review the PR? Thanks. |
| @@ -0,0 +1,815 @@ | |||
| { | |||
There was a problem hiding this comment.
I think the questions is if I have a set of .wav files, what part of this script needs to be changed?
Better if this can take a custom directory and require no code changes from user.
Reply via ReviewNB
There was a problem hiding this comment.
Good question. I added a paragraph in this header section to answer that question.
| @@ -0,0 +1,815 @@ | |||
| { | |||
There was a problem hiding this comment.
There was a problem hiding this comment.
Yes. We can safely assume that these libraries are all pre-installed for the following reasons:
- They are installed by default on Google Colab.
- These three are such widely-used libraries that virtually all data scientists and ML practitioners know how to install them.
|
Ping @pyu10055 if you can take another look at the PR, it would be great. Thanks. |
There was a problem hiding this comment.
Reviewed 1 of 1 files at r5.
Reviewable status:complete! 1 of 1 approvals obtained (waiting on @pyu10055)
|
Thanks for the reviews, @pyu10055 and @lintian06. Merging PR. |
in Python, using a set of .wav files.
Fixes tensorflow/tfjs#3719
This change is