Downloads · 30 days
0
DACVAE-Arabic-32dim
sherif1313/DACVAE-Arabic-32dim
DACVAE-Arabic-32dim is a machine learning model from sherif1313. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
VAE version of the Descript Audio Codec, which has a continuous latent space. Descript Audio Codec (DAC) is a high fidelity general neural audio codec, introduced in the paper titled High-Fidelity Audio Compression wi…
Access
Public
Updated May 18, 2026
Repo size
430 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth430 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 29, 2026
- Updated
- May 18, 2026
- SHA
- cdf438ec
Model card
From the Hugging Face model README
VAE version of the Descript Audio Codec, which has a continuous latent space. Descript Audio Codec (DAC) is a high fidelity general neural audio codec, introduced in the paper titled High-Fidelity Audio Compression with Improved RVQGAN. Most code is adopted from the open-source repo DAC
According to the Semantic-VAE paper, this semantic distillation approach improves the training efficiency and performance of downstream TTS models. Furthermore, by reducing the latent dimension to 32, this new variant enables even lighter and faster training for these downstream tasks without sacrificing much audio quality.
Thanks to
facebook/dacvae-watermarked
Aratako/Semantic-DACVAE-Japanese-32dim
- License
- apache-2.0
- Created
- Apr 29, 2026
- Updated
- May 18, 2026