Describe the bug
Here
|
model = model.fit(features_list) |
You use .fit method on partial of the data. However, I think this should be partial_fit() to update on a small chunk of data. If you call .fit. The kmeans will only apply to that specific data while removing all the previous results.
But I am also not so sure. If this is the case, all experiments built on kmeans would be wrong.
Expected behaviour
Please consider changing the line of code.
To Reproduce
No response
Environment Details
No response
Relevant Log Output
No response
Additional Context
No response
Describe the bug
Here
speechbrain/speechbrain/utils/kmeans.py
Line 171 in 431760b
You use .fit method on partial of the data. However, I think this should be partial_fit() to update on a small chunk of data. If you call .fit. The kmeans will only apply to that specific data while removing all the previous results.
But I am also not so sure. If this is the case, all experiments built on kmeans would be wrong.
Expected behaviour
Please consider changing the line of code.
To Reproduce
No response
Environment Details
No response
Relevant Log Output
No response
Additional Context
No response