---
license: cc-by-4.0
pipeline_tag: sentence-similarity
tags:
- espnet
- audio
- singing voice synthesis
---


## 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](https://github.com/espnet/espnet/).

### Demo: How to use in ESPnet2

Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
if you haven't done that already.