ONNX Model Zoo

LEMAS-Project/LEMAS-Edit

By LEMAS-Project · ↓ 10 · ♥ 2 · Updated 2026-01-10

What's in this repo

This page lists the files in LEMAS-Project/LEMAS-Edit, including denoiser_model.onnx, Kim_Vocal_1.onnx.

  • 2 ONNX models (.onnx files)
  • 29 files, including 8 .json, 2 .md, 2 .pth, 2 .safetensors, 2 .bin, 2 .txt
  • Last updated 2026-01-10

ONNX files

File Size Download
pretrained_models/denoiser_model.onnx — Download
pretrained_models/uvr5/Kim_Vocal_1.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

LEMAS-Edit

LEMAS-Edit is a multilingual speech editing system, presented in the paper LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models.

Supported Languages

The model supports 10 major languages for zero-shot synthesis:

  • Chinese (zh)
  • English (en)
  • Spanish (es)
  • Russian (ru)
  • French (fr)
  • German (de)
  • Italian (it)
  • Portuguese (pt)
  • Indonesian (id)
  • Vietnamese (vi)

Citation

@article{zhao2026lemas,
  title={LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models},
  author={Zhao, Zhiyuan and Lin, Lijian and Zhu, Ye and Xie, Kai and Liu, Yunfei and Li, Yu},
  journal={arXiv preprint arXiv:2601.04233},
  year={2026}
}

Model info

onnx zero-shot multilingual text-to-speech it pt es fr de vi id ru
↓ 10 ♥ 2

Created: 2026-01-09

Updated: 2026-01-10

View on Hugging Face

Files (29)

.gitattributes
README.md
config.json
pretrained_models/ckpts/autoregressive/config.json
pretrained_models/ckpts/autoregressive/dac_SR_8codes_2048_hop960_speech.pth
pretrained_models/ckpts/autoregressive/encodec_4cb2048_giga.th
pretrained_models/ckpts/autoregressive/multilingual_330M.pth
pretrained_models/ckpts/multilingual_grl/multilingual_grl.safetensors
pretrained_models/ckpts/multilingual_prosody/multilingual_prosody.safetensors
pretrained_models/ckpts/prosody_encoder/pretssel_cfg.json
pretrained_models/ckpts/prosody_encoder/prosody_encoder_UnitY2.pt
pretrained_models/ckpts/vocos-mel-24khz/.gitattributes
pretrained_models/ckpts/vocos-mel-24khz/README.md
pretrained_models/ckpts/vocos-mel-24khz/config.yaml
pretrained_models/ckpts/vocos-mel-24khz/pytorch_model.bin
pretrained_models/data/multilingual_grl/vocab.txt
pretrained_models/data/multilingual_prosody/vocab.txt
pretrained_models/demos/lemas_edit_test/align/en_AUD0000000214_S0001522.json
pretrained_models/demos/lemas_edit_test/align/zh_emilia_zh_0008385782.json
pretrained_models/demos/lemas_edit_test/vocals/en_AUD0000000214_S0001522.mp3
pretrained_models/demos/lemas_edit_test/vocals/zh_emilia_zh_0008385782.mp3
pretrained_models/demos/test.wav
pretrained_models/denoiser_model.onnx ONNX
pretrained_models/uvr5/Kim_Vocal_1.onnx ONNX
pretrained_models/uvr5/MDX-Net-Kim-Vocal1.json
pretrained_models/uvr5/model_data.json
pretrained_models/uvr5/model_name_mapper.json
pretrained_models/whisperx/whisperx-vad-segmentation.bak
pretrained_models/whisperx/whisperx-vad-segmentation.bin

Related models