niobures/U-Net
By niobures · ↓ 0 · ♥ 0 · Updated 2025-10-24
What's in this repo
This page lists the files in niobures/U-Net, including unet_mobilenet_v2_best.onnx, RefineSpectrogramUnet.best.opt.onnx, second_voice_bank.best.opt.onnx and more.
- 4 ONNX models (.onnx files)
- 91 files, including 42 .wav, 9 .txt, 6 .mp4, 4 .onnx, 4 .chkpt, 3 .md
- Last updated 2025-10-24
ONNX files
| File | Size | Download |
|---|---|---|
| models/UnetONNX/unet_mobilenet_v2_best.onnx | — | Download |
| models/ailia-models/RefineSpectrogramUnet.best.opt.onnx | — | Download |
| models/ailia-models/second_voice_bank.best.opt.onnx | — | Download |
| models/unet-fp16-onnx/unet-fp16.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.
No README provided by the author.
Files (91)
.gitattributes
Funnel Deep Complex U-Net for Phase-Aware Speech Enhancement.pdf
Phase-aware Speech Enhancement with Deep Complex U-Net.pdf
code/DCUnet.zip
code/source_separation [AppleHolic].zip
colab/Source_Separation_first_notebook.ipynb
models/DCUNet_Libri1Mix_enhsingle_16k/.gitattributes
models/DCUNet_Libri1Mix_enhsingle_16k/README.md
models/DCUNet_Libri1Mix_enhsingle_16k/pytorch_model.bin
models/DCUNet_Libri1Mix_enhsingle_16k/source.txt
models/DCUnet/source.txt
models/DCUnet/weights.pth
models/UnetONNX/.gitattributes
models/UnetONNX/README.md
models/UnetONNX/source.txt
models/UnetONNX/unet_mobilenet_v2_best.onnx
ONNX
models/ailia-models/RefineSpectrogramUnet.best.opt.onnx
ONNX
models/ailia-models/RefineSpectrogramUnet.best.opt.onnx.prototxt
models/ailia-models/code/049 - Young Griffo - Facade.wav
models/ailia-models/code/LICENSE
models/ailia-models/code/README.md
models/ailia-models/code/doublenoble_k7rain_part.wav
models/ailia-models/code/requirements.txt
models/ailia-models/code/unet_source_separation.py
models/ailia-models/code/unet_source_separation_utils.py
models/ailia-models/code/unet_source_separation_utils_ailia.py
models/ailia-models/second_voice_bank.best.opt.onnx
ONNX
models/ailia-models/second_voice_bank.best.opt.onnx.prototxt
models/ailia-models/source.txt
models/noise-reduction-resnet-unet/.gitattributes
models/noise-reduction-resnet-unet/model.pb
models/noise-reduction-resnet-unet/source.txt
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/Samples Info, License.docx
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/doublenoble_k7rain_part.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/doublenoble_k7rain_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/overwatch_kim_part.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/overwatch_kim_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/pubg_start_part.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/pubg_start_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/yumdaeng_car_part.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/yumdaeng_car_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/yupdduk_part.wav
models/source_separation/predicted-samples/general-voice-source-separation/test-samples/yupdduk_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/194_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/194_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/194_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/241_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/241_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/241_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/244_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/244_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/244_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/253_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/253_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/253_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/276_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/276_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/276_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/448_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/448_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/448_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/514_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/514_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/514_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/520_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/520_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/520_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/549_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/549_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/549_pred.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/608_clean.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/608_noise.wav
models/source_separation/predicted-samples/general-voice-source-separation/validation-10-random-samples/608_pred.wav
models/source_separation/predicted-samples/singing-voice-separation/CHEEZE _ 치즈 - 1.5집 Plain 03. 모두의 순간 (Voice Separation Sample) - Appleholic (480p, h264).mp4
models/source_separation/predicted-samples/singing-voice-separation/Pushing Me Away - Linkin Park (Hybrid Theory) (Voice Separation Sample) - Appleholic (480p, h264).mp4
models/source_separation/predicted-samples/singing-voice-separation/권진아(Kwon Jin Ah) - 그대만 보여요(I Only See You) (Voice Only) - Appleholic (480p, h264).mp4
models/source_separation/predicted-samples/singing-voice-separation/백예린 (Baek Ye Rin) - 그의 바다 (His Ocean) (Voice Separation Sample) - Appleholic (480p, h264).mp4
models/source_separation/predicted-samples/singing-voice-separation/성시경 (Sung Si Kyung) - 거리에서 (On the street) Voice Shift - Appleholic (480p, h264).mp4
models/source_separation/predicted-samples/singing-voice-separation/태연 (TAEYEON) - 사계 (Four Seasons) (Voice Separation Sample) - Appleholic (480p, h264).mp4
models/source_separation/pretrained_checkpoint/general-voice-source-separation/dsd100 - voice bank joint/RefineSpectrogramUnet.best.chkpt
models/source_separation/pretrained_checkpoint/general-voice-source-separation/voice bank/first_voice_bank.best.chkpt
models/source_separation/pretrained_checkpoint/general-voice-source-separation/voice bank/second_voice_bank.best.chkpt
models/source_separation/pretrained_checkpoint/general-voice-source-separation/voice bank/version, tag.docx
models/source_separation/pretrained_checkpoint/singing-voice-separation/RefineSpectrogramUnet.best.chkpt
models/source_separation/source.txt
models/speech-enhancement-unet/.gitattributes
models/speech-enhancement-unet/model.pb
models/speech-enhancement-unet/source.txt
models/unet-fp16-onnx/.gitattributes
models/unet-fp16-onnx/source.txt
models/unet-fp16-onnx/unet-fp16.onnx
ONNX
Related models
More from niobures
More models
No task type declared.