Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
TTS fine-tuning for SpeechT5 #21824
TTS fine-tuning for SpeechT5 #21824
Changes from all commits
5b15e26
6452ec3
2cc9c89
9bf24d1
651be98
6e3c3f2
4acaf1b
75b13fd
9473f93
3c0b202
aee0272
193e6d1
2a81ec4
218830c
a05b2ea
7d803ae
1be2f8b
40e7057
92f79a6
f4edf81
7c2a44c
0dea7f5
81668a2
ff83735
9a02068
cf67785
0ac8589
03bc390
0b2785e
b0558ac
94b61bc
5d2f774
39f0f8b
ab501a4
630f97a
614f7aa
a74e414
671c44b
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🔥 Kudos for using the audio utils! Simplifies a lot
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Long term, would it make sense for an stft function to go in audio utils?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes absolutely. And that would also remove the "must be a power of two" limitation.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also we should be able to batch the stft (long term goal)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Am I correct in understanding that this reduction now takes place in
shift_spectrograms_right
in the modelling file?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Correct, I mistakenly thought it applied to the labels but it applies to the input that the decoder sees.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice 😉