Downloads · 30 days
0
speech-info-compression-prosody-projector-commonvoice
lingchensanwen/speech-info-compression-prosody-projector-commonvoice
speech-info-compression-prosody-projector-commonvoice is a machine learning model from lingchensanwen. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch.
This repository contains a preliminary research checkpoint for speech information compression experiments.
Access
Public
Updated Apr 27, 2026
Repo size
25.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt25.2 MB · 99%
At a glance
- Library
- pytorch
- Access
- Public
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026
- SHA
- 69cb4136
Base models
Model card
From the Hugging Face model README
Speech Info Compression Checkpoint
This repository contains a preliminary research checkpoint for speech information compression experiments.
Files
prosody_projector.pt: trained projector checkpointprosody_loss_log.csv: training loss log
Training Summary
The checkpoint was trained on a small CommonVoice-derived audio pool for 3 epochs. The epoch-average training loss decreased from 0.0408 to 0.0308.
Caveat
This is an early experimental artifact. It is provided for collaboration and reproducibility, and does not by itself establish downstream task improvements.
- Library
- pytorch
- Created
- Apr 27, 2026
- Updated
- Apr 27, 2026