-
Notifications
You must be signed in to change notification settings - Fork 2.3k
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 tutorial update: use speaker 9017 instead of 6097 #5532
Conversation
Signed-off-by: Jocelyn Huang <[email protected]>
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.
Why pitch statistics calculation is outside of the scope of this tutorial? model.pitch_mean=152.3 model.pitch_std=64.0 model.pitch_fmin=30 model.pitch_fmax=512
@@ -326,7 +326,7 @@ | |||
"`\n", |
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.
In general, it's better to use this whitelist: https://github.com/NVIDIA/NeMo/blob/main/nemo_text_processing/text_normalization/en/data/whitelist/tts.tsv
, not needed for hi-fi tts as it's already normalized
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.
Should be a quick change. Would you prefer it in this PR or a new one?
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.
up to you. Some checks are still running - hmm, it's been 19+ hrs since the last commit
Signed-off-by: Jocelyn Huang <[email protected]>
Signed-off-by: Jocelyn Huang <[email protected]>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <[email protected]> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <[email protected]> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <[email protected]> Signed-off-by: Jocelyn Huang <[email protected]> Signed-off-by: Hainan Xu <[email protected]>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <[email protected]> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <[email protected]> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <[email protected]> Signed-off-by: Jocelyn Huang <[email protected]> Signed-off-by: Hainan Xu <[email protected]>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <[email protected]> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <[email protected]> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <[email protected]> Signed-off-by: Jocelyn Huang <[email protected]> Signed-off-by: andrusenkoau <[email protected]>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <[email protected]> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <[email protected]> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <[email protected]> Signed-off-by: Jocelyn Huang <[email protected]>
Signed-off-by: Jocelyn Huang [email protected]
What does this PR do ?
Replaces speaker 6097's data with speaker 9017's since the latter has given explicit permission.
Collection: TTS
Changelog
Usage