Notebooks to investigate data set bias in audio embeddings
No README available, please check again later.
无需情感标注的情感可控语音合成模型,基于VITS
Some HRTF experiments I made.
AudioLDM text to audio colab
Nearest Neighbor Imputation to Repair Damaged Audio
BAD-VAE: A VAE framework for unsupervised disentanglement of sequential data
Convenience functions to finetune the XLSR-Wav2vec2 speech transcription model
Reproducing code for Learning Disentangled Representations of Timbre and Pitch for Musical Instru...
with keras data set we load a data base and train our machine for test
my-deeplearning-practice-notebooks
Tools to train a generative model on arbitrary audio samples
A set of examples for basic audio data handling
Machine Learning applied to sound