Merge pull request CNChTu#35 from OOPPEENN/main

Clean
sandyzikun · Jul 27, 2023 · eb8ce85 · eb8ce85
2 parents 2227b43 + a6c02f8
commit eb8ce85
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -134,9 +134,9 @@ python train.py -c configs/config.yaml
 |--------------------------------------------------------------------------------|--------|------------|-------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|
 | [contentvec768l12](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*30 | 100        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/datasets/ms903/Diff-SVC-refactor-pre-trained-model/resolve/main/Diffusion-SVC/shallow_512_30/model_0.pt) |
 | [contentvec768l12](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*20 | 200        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/datasets/ms903/Diff-SVC-refactor-pre-trained-model/resolve/main/Diffusion-SVC/shallow_512_20/model_0.pt) |
-| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*20 | 200        | VCTK<br/>m4singer<br/>PTDB<br/>kiritan<br/>opencpop<br/>popcs | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_51220_k200.zip) |
-| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 768*30 | 200        | VCTK<br/>m4singer<br/>PTDB<br/>kiritan<br/>opencpop<br/>popcs | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_76830_k200.zip) |
-| [whisper-ppg(仅支持sovits)](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt) | 768*30 | 200        | PTDB<br/>m4singer<br/>kiritan<br/>opencpop<br/>pjs_corpus<br/>popcs | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/whisper_medium_vol_76830_k200.zip) |
+| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*20 | 200        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_51220_k200.zip) |
+| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 768*30 | 200        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_76830_k200.zip) |
+| [whisper-ppg(仅支持sovits)](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt) | 768*30 | 200        | PTDB<br/>m4singer | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/whisper_medium_vol_76830_k200.zip) |
 - **实验发现naive模型在小数据上有音域问题，请优先考虑用较少的步数微调naive模型或直接使用无限音域的ddsp模型**
 
 ### 2.3 和2.2配套的Naive预训练模型和DDSP预训练模型

diff --git a/README_en.md b/README_en.md
@@ -136,9 +136,9 @@ Here is an additional special pre-trained model using the contentvec768l12 encod
 |--------------------------------------------------------------------------------|--------------|------------|-------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|
 | [contentvec768l12](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*30       | 100        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/datasets/ms903/Diff-SVC-refactor-pre-trained-model/resolve/main/Diffusion-SVC/shallow_512_30/model_0.pt) |
 | [contentvec768l12](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*20       | 200        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/datasets/ms903/Diff-SVC-refactor-pre-trained-model/resolve/main/Diffusion-SVC/shallow_512_20/model_0.pt) |
-| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*20        | 200        | VCTK<br/>m4singer<br/>PTDB<br/>kiritan<br/>opencpop<br/>popcs | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_51220_k200.zip) |
-| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 768*30        | 200        | VCTK<br/>m4singer<br/>PTDB<br/>kiritan<br/>opencpop<br/>popcs | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_76830_k200.zip) |
-| [whisper-ppg(only can use with sovits)](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt) | 768*30 | 200        | PTDB<br/>m4singer<br/>kiritan<br/>opencpop<br/>pjs_corpus<br/>popcs | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/whisper_medium_vol_76830_k200.zip) |
+| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 512*20        | 200        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_51220_k200.zip) |
+| [contentvec256l9](https://ibm.ent.box.com/s/z1wgl1stco8ffooyatzdwsqn2psd9lrr) | 768*30        | 200        | VCTK<br/>m4singer | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/vec256l9_vol_76830_k200.zip) |
+| [whisper-ppg(only can use with sovits)](https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt) | 768*30 | 200        | PTDB<br/>m4singer | [HuggingFace](https://huggingface.co/OOPPEENN/Diffusion-SVC-pretrained-models/resolve/main/whisper_medium_vol_76830_k200.zip) |
 - **The experiment found that the Naive model has f0 range issues on small data. Please prioritize fine-tuning the Naive model with fewer steps or directly using the infinite range ddsp model.**
 
 ### 2.3 Naive pre training model and DDSP pre training model matched with 2.2