-
Notifications
You must be signed in to change notification settings - Fork 177
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
Cannot change speaker for interpolation #35
Comments
You need to make sure z_1 and z_2 produce samples from different speakers. |
I have also I keep sampling z_2, performing inference and listening to the samples produced with z_2 but the speaker's voice sounds the same as the voice produced with z_1. By the way, it is always a female voice. Do you have any idea why this might be happening ? |
Are you using the LibriTTS model? |
Yes I am using the LibriTTS model |
Hey Damien, the pre-trained LibriTTS model available in our repo has speaker embeddings. You need to train a model without speaker embeddings, i.e. You can warm-start from the pre-trained LibriTTS model with speaker embeddings. |
Hello,
I am trying to interpolate between two speakers. I am using the model pretrained on LibriTTS.
I have read the issue "How is interpolation between speakers performed?" #33 but I still cannot manage to make it work.
Here are the steps I have followed:
gate_threshold = 1
(as mentioned in How is interpolation between speakers performed? #33)torch.manual_seed(seed)
andtorch.cuda.manual_seed(seed)
from inference.pygate_threshold = 0.5
But when sampling z_1 and z_2, even multiple times, after generating the spectrogram with the pretrained Flowtron and generating the audio with the pretrained WaveGlow, the speaker sounds the same, only the audio quality seems to vary. (z_1 and z_2 have different values)
gate_threshold = 0.5
before interpolation?gate_threshold = 1
in the first place when looking for z_1 and z_2?Thanks
The text was updated successfully, but these errors were encountered: