UniSpeech
voicefilter
UniSpeech | voicefilter | |
---|---|---|
1 | 1 | |
390 | 1,032 | |
1.3% | 1.1% | |
4.5 | 0.0 | |
about 1 month ago | 3 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
UniSpeech
-
[D] What's stopping you from working on speech and voice?
- https://github.com/microsoft/UniSpeech
voicefilter
-
What does width mean in this context? I can't find it anywhere. It's not stride because it would be in compatible with the dilation rate in layer 4. Any ideas? This is from the VoiceFilter paper
Here's the link: https://github.com/mindslab-ai/voicefilter/blob/master/model/model.py
What are some alternatives?
VBx - Variational Bayes HMM over x-vectors diarization
asteroid - The PyTorch-based audio source separation toolkit for researchers
speechbrain - A PyTorch-based Speech Toolkit
thunder-speech - A Hackable speech recognition library.
Conv-TasNet - A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
hifigan-denoiser - HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
espnet - End-to-End Speech Processing Toolkit
ECAPA-TDNN - Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
Kaldi Speech Recognition Toolkit - kaldi-asr/kaldi is the official location of the Kaldi project.
NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)