-
hi, I have tested neural plc using different nn model. opus-ng deep plc seems to have a worse plc audio quality than opus lpcnet plc. How can I increase the plc quality?
-
**Is your feature request related to a problem? Please describe.**
After operating on audio frames that have been created using `librosa.util.frame`, I would like easily to have an inverse transfor…
-
-
In my speech synthesis system built from Merlin toolkit, it take long time to generate speech from text. Most of the time used by World Vocoder and DNN generation module. So, to improve time delay, I …
-
I get this error when running '!python agent.py --config config.yaml'
/content/muzic/musicagent
2023-12-04 10:03:54.786370: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow bin…
-
Hi @Rayhane-mamah,
my corpus ~2.5-hour Single-Speaker Speech, Each audio file is Maximum 16 seconds Which are attached below file train.txt and hparams.py.
import tensorflow as tf
import numpy a…
-
Anyone tried to use a different, more recent (and supposedly) better vocoder ?
HiFI-Gan is already a bit old and better options appeared like [BIGVGAN](https://github.com/NVIDIA/BigVGAN) and maybe …
-
Hi all, first thanks @Rayhane-mamah for fixing bugs in wavenet vocoder and making it fully work now :) I've spent several days looking into its implementation and there's a part that really makes me s…
-
it seems T5 embedding from FrozenT5 has shape (B, max_length, D)
https://github.com/yangdongchao/LLM-Codec/blob/e21c1bff56fa40d46e42f2906838129aa4f2003d/codec/MSCodec.py#L73-L78
is text_feature …
-
# The Bottish Play
_A computer speech audio production of Shakespeare's "Macbeth"_
# [Listen to the Final Production](https://www.youtube.com/watch?v=4Rm85rMs6Tw)
## [Listen to the Encore](https://…