Downloads · 30 days
0
PASQA
ly-corporation/PASQA
PASQA is a machine learning model from ly-corporation. 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.
Pretrained checkpoint for PASQA, an SSL-based MOS prediction model that estimates the perceptual quality of synthesized Japanese speech with a focus on pitch-accent correctness.
Access
Public
Updated Jun 17, 2026
Repo size
1.5 GB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.pkl753 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 9, 2026
- Updated
- Jun 17, 2026
- SHA
- 7fe0bfc7
Model card
From the Hugging Face model README
PASQA — Pitch-Accent-Focused Speech Quality Assessment Model
Pretrained checkpoint for PASQA, an SSL-based MOS prediction model that estimates the perceptual quality of synthesized Japanese speech with a focus on pitch-accent correctness.
The model is developed by LY Corporation and released alongside our INTERSPEECH 2026 paper.
Usage
Inference is done with the code in the PASQA repository. See the repository for setup and usage instructions.
License
These model parameters are released under the Apache License 2.0.
- License
- apache-2.0
- Languages
- ja
- Created
- Jun 9, 2026
- Updated
- Jun 17, 2026