Downloads · 30 days
0
joycent-medium-no-grl
walston/joycent-medium-no-grl
joycent-medium-no-grl is a text-to-speech model from walston. Use it when you need text read aloud. It is set up for pytorch. The card lists the license as mit.
This Joycent Mandarin accent TTS acoustic model was trained using accent embeddings extracted by walston/whisaid-medium-no-grl. The released checkpoint is epoch 100.
Access
Public
Updated Aug 16, 2026
Repo size
228 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt228 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Aug 16, 2026
- Updated
- Aug 16, 2026
- SHA
- 89acca3d
Model card
From the Hugging Face model README
Joycent trained with WhisAID accent embeddings
This Joycent Mandarin accent TTS acoustic model was trained using accent embeddings extracted by walston/whisaid-medium-no-grl. The released checkpoint is epoch 100.
- Accent encoder: walston/whisaid-medium-no-grl
- Vocoder: walston/joycent-vocoder
Download
from huggingface_hub import hf_hub_download
checkpoint_path = hf_hub_download(
repo_id="walston/joycent-medium-no-grl",
filename="grad_100.pt",
)
Pass the path to joycent/inference_joycent.py with
--acoustic-checkpoint. Full synthesis also requires the Joycent vocoder.
Checkpoint
- Epoch: 100
- Acoustic model: Joycent / Grad-TTS
- Accent embedding dimension: 256
- Task
- Text-to-Speech
- Library
- pytorch
- License
- mit
- Created
- Aug 16, 2026
- Updated
- Aug 16, 2026