deterministic-algorithms-lab/Cross-Lingual-Voice-Cloning
Tacotron 2 - PyTorch implementation with faster-than-realtime inference modified to enable cross lingual voice cloning.
Jupyter NotebookBSD-3-Clause
Issues
- 0
Sample dataset and train, validation files?
#25 opened by RahulBhalley - 0
Unable to achieve cross-lingual cloning
#27 opened by supernirmesh - 3
Attention Alignment Not Working
#19 opened by jinny1208 - 1
Problem with the input mel length
#11 opened by TinBarbie - 0
Does onboarding a new speaker after a model is trained require tr-training from scratch?
#16 opened by vivekkalyanarangan30 - 0
How many hours of speech and epochs it takes to get the quality as in paper?
#14 opened by fancat-programer - 10
code-switch speech have different voice
#10 opened by c9412600 - 1
Input text type
#8 opened by leijue222 - 27
Train failed because the loss is nan
#3 opened by JoeyHeisenberg - 3
speaker_embedding_dimension
#9 opened by tshmak - 2
Available pre-trained model?
#7 opened by antonibigata - 1
Meaning of _o and _l in residual_encoder
#5 opened by tshmak - 2
index out of range
#4 opened by taichuai - 1
RuntimeError: CUDA error: out of memory
#1 opened by 60999 - 1
What all changes needs to be done in text files, if i want to do it for hindi and english crosslingual model
#2 opened by akashicMarga