crlandsc / torch-log-wmse
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
☆28Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for torch-log-wmse
- ☆40Updated 5 months ago
- Source code of APNet2, a vocoder☆51Updated last year
- Robust Singing Voice Transcription and MIDI Extraction☆58Updated this week
- ☆59Updated last week
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆72Updated 2 months ago
- Speech Human Evaluation Estimation Toolkit (SHEET)☆41Updated last week
- Prosody and Pronunciation Modification Network☆44Updated 3 months ago
- ☆34Updated 5 months ago
- Unofficial implementation of NANSY++ in Pytorch Lightning☆49Updated 8 months ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆54Updated last year
- ☆21Updated 7 months ago
- [InterSpeech 24] FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter☆78Updated 4 months ago
- ☆42Updated this week
- ☆45Updated this week
- Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction☆50Updated 2 weeks ago
- Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"☆84Updated 2 months ago
- ☆47Updated last week
- TS-BSmamba2: A TWO-STAGE BAND-SPLIT MAMBA-2 NETWORK FOR MUSIC SEPARATION☆37Updated 2 months ago
- ☆87Updated 2 years ago
- Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"☆45Updated 7 months ago
- Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing☆68Updated last year
- Please visit https://thuhcsi.github.io/SnakeGAN/☆36Updated last year
- Contains the code associated with the ICLR submission for our text-to-speech diffusion model☆50Updated last year
- PAM is a no-reference audio quality metric for audio generation tasks☆49Updated 4 months ago
- Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986☆37Updated last month
- Bandwidth Extension of Historical Recordings using Generative Adversarial Networks☆34Updated last year
- AudioSR-Upsampling (any -> 48kHz)☆38Updated 9 months ago
- ☆50Updated 3 weeks ago
- VAE modified from Descript Audio Codec, which replaces the RVQ with VAE☆54Updated 7 months ago
- Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications☆63Updated 2 months ago