-
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 <jocelynh@nvidia.com>
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 <jocelynh@nvidia.com>
Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Signed-off-by: Hainan Xu <hainanx@nvidia.com>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Signed-off-by: Hainan Xu <hainanx@nvidia.com>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Signed-off-by: andrusenkoau <andrusenkoau@gmail.com>
* TTS tutorial update: speaker 9017 instead of 6097 Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Update whitelist path to tts.tsv Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Add some info about getting pitch stats to TTS fine-tuning tutorial Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com>
Signed-off-by: Jocelyn Huang jocelynh@nvidia.com
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