Downloads · 30 days
1
7% of all-time downloads
opencpop_svs_train_toksing_300epoch-multi_hl6_wl6_wl23
espnet/opencpop_svs_train_toksing_300epoch-multi_hl6_wl6_wl23
opencpop_svs_train_toksing_300epoch-multi_hl6_wl6_wl23 is a text-to-speech model from espnet. Use it when you need text read aloud.
All-time downloads
15
Public
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pkl1.1 GB · 79%
At a glance
- Task
- Text-to-Speech
- Access
- Public
- Created
- Jun 16, 2025
- Updated
- Sep 18, 2026
- SHA
- 19462d11
Model card
From the Hugging Face model README
Model Arch: TokSing
Dataste: Opencpop
You can run this model with espnet/svs2.
./run.sh --stage 8 \
--kmeans_feature "multi/hubert_large_6+wavlm_large_6+wavlm_large_23" \
--multi_token "hubert_large_ll60k_128_6 wavlm_large_128_6 wavlm_large_128_23" \
--inference_model 300epoch.pth \
--vocoder_file {vocoder_path}
license: cc-by-4.0
- Task
- Text-to-Speech
- Created
- Jun 16, 2025
- Updated
- Sep 18, 2026