so-vits-svc fork with realtime support, improved interface and more features.
Self-Supervised Speech Pre-training and Representation Learning Toolkit
Phoneme segmentation using pre-trained speech models
[ICASSP 2023] Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained Representations
unsupervised spoken utterances scoring
code for our paper DistilALHuBERT: A Distilled Parameter Sharing Audio Representation Model
Functionality for speech data processing including time alignment, encoding with speech encoders (tokenizers) and data preprocessing of common datasets
This repository contains different approaches I tried for improving ASR systems for accented English speech. All of them use the HuBERT model as baseline
Pipeline for generating images conditioned on input audio
Add a description, image, and links to the hubert topic page so that developers can more easily learn about it.
To associate your repository with the hubert topic, visit your repo's landing page and select "manage topics."