Downloads · 30 days
9
5% of all-time downloads
mixdata_svs_visinger2_spkembed_lang_pretrained
espnet/mixdata_svs_visinger2_spkembed_lang_pretrained
mixdata_svs_visinger2_spkembed_lang_pretrained is a sentence similarity model from espnet. Use it when you need a score for how close two texts are. It is set up for espnet. The card lists the license as cc-by-4.0.
Dataset (abbreviations for some datasets): mixdata including opencpop, acesinger, m4singer, ameboshi, kiritan, onikukurumiutagoedb, ofutonputagoedb, namineritsuutagoedb, itako, pjs.
All-time downloads
190
Public
Repo size
448 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth448 MB · 100%
At a glance
- Task
- Sentence Similarity
- Library
- espnet
- License
- cc-by-4.0
- Access
- Public
- Created
- Oct 24, 2024
- Updated
- Jul 2, 2025
- SHA
- bb2ceb61
Model card
From the Hugging Face model README
Warning: This model has already been deprecated. You can visit our new trained model (https://huggingface.co/espnet/mixdata_svs_visinger2_spkemb_lang_pretrained).
ESPnet2 SVS model
espnet/mixdata_svs_visinger2_spkembed_lang_pretrained
Dataset (abbreviations for some datasets): mixdata including opencpop, acesinger, m4singer, ameboshi, kiritan, oniku_kurumi_utagoe_db, ofuton_p_utagoe_db, namine_ritsu_utagoe_db, itako, pjs.
recipe: egs/mixed/svs1
model: VISinger2 in 44k with spk_embedding model, multi-language
This model was trained by TangRain using acesinger recipe in espnet.
Demo: How to use in ESPnet2
Follow the ESPnet installation instructions if you haven't done that already.
- Task
- Sentence Similarity
- Library
- espnet
- License
- cc-by-4.0
- Created
- Oct 24, 2024
- Updated
- Jul 2, 2025