mirror of
https://github.com/w-okada/voice-changer.git
synced 2025-01-23 05:25:01 +03:00
英語版アップデートとreadmeからのリンクの張替え
This commit is contained in:
nadare
parent
29be0775ec
commit
005880cd78
@ -76,7 +76,7 @@ Windows 版と Mac 版を提供しています。
|
||||
- DDSP-SVC の動作には、hubert-soft と enhancer のモデルが必要です。hubert-soft は[このリンク](https://github.com/bshall/hubert/releases/download/v0.1/hubert-soft-0d54a1f4.pt)からダウンロードして、バッチファイルがあるフォルダに格納してください。enhancer は[このサイト](https://github.com/openvpi/vocoders/releases/tag/nsf-hifigan-v1)から`nsf_hifigan_20221211.zip`ダウンロードして下さい。解凍すると出てくる`nsf_hifigan`というフォルダをバッチファイルがあるフォルダに格納してください。
|
||||
- DDPS-SVC の encoder は hubert-soft のみ対応です。
|
||||
|
||||
- RVC で使用する場合の GUI の各項目説明は[こちら](tutorials/tutorial_rvc_ja.md)をご覧ください
|
||||
- RVC で使用する場合の GUI の各項目説明は[こちら](tutorials/tutorial_rvc_ja_latest.md)をご覧ください
|
||||
|
||||
- ダウンロードはこちらから。
|
||||
|
||||
|
||||
@ -77,7 +77,7 @@ We offer Windows and Mac versions.
|
||||
|
||||
- The encoder of DDPS-SVC only supports hubert-soft.
|
||||
|
||||
- Please refer to [here](tutorials/tutorial_rvc_en.md) for the description of each item of GUI to be used in RVC.
|
||||
- Please refer to [here](tutorials/tutorial_rvc_en_latest.md) for the description of each item of GUI to be used in RVC.
|
||||
|
||||
- Download (When you cannot download from google drive, try [hugging_face](https://huggingface.co/wok000/vcclient000/tree/main))
|
||||
|
||||
|
||||
@ -1,13 +1,15 @@
|
||||
# Realtime Voice Changer Client for RVC Tutorial (v.1.5.2.4)
|
||||
# Realtime Voice Changer Client for RVC Tutorial (v.1.5.2.5)
|
||||
|
||||
# Introduction
|
||||
|
||||
This application is client software for real-time voice conversion that supports various voice conversion models. This document provides a description for voice conversion limited to [RVC(Retrieval-based-Voice-Conversion)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI).
|
||||
|
||||
From the following, the original [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) is referred to as the original-RVC, [RVC-WebUI](https://github.com/ddPn08/rvc-webui) created by ddPn08 is referred to as ddPn08-RVC.
|
||||
|
||||
## Notes
|
||||
|
||||
- Model training must be done separately.
|
||||
- If you want to learn by yourself, please go to [RVC(Retrieval-based-Voice-Conversion)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI).
|
||||
- If you want to learn by yourself, please go to [original-RVC](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI) or [ddPn08RVC](https://github.com/ddPn08/rvc-webui).
|
||||
- [Recording app on Github Pages](https://w-okada.github.io/voice-changer/) is convenient for preparing voice for learning on the browser.
|
||||
- [Commentary video] (https://youtu.be/s_GirFEGvaA)
|
||||
- [TIPS for training](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/training_tips_en.md) has been published, so please refer to it.
|
||||
@ -37,13 +39,14 @@ When connecting remotely, please use `.bat` file (win) and `.command` file (mac)
|
||||
|
||||
It is successful if the Launcher screen like the one below appears. Select RVC from this screen.
|
||||
|
||||
<img src="/tutorials/images/launcher.png" alt="launcher" width="800" loading="lazy">
|
||||
|
||||
|
||||
## Screen for RVC
|
||||
|
||||
It is successful if the following screen appears.
|
||||
|
||||
<img src="/tutorials/images/RVC_GUI.png" alt="launcher" width="800" loading="lazy">
|
||||
|
||||
|
||||
|
||||
## GUI item details
|
||||
|
||||
@ -76,37 +79,47 @@ This is the time it takes to convert data that is the sum of Input Chunk and Ext
|
||||
Get information held by the server. If information synchronization between server and client seems not to be successful, please press the Reload button.
|
||||
|
||||
### Switch Model
|
||||
|
||||
You can switch between uploaded models.
|
||||
Information about the model is shown in [] under the name
|
||||
1. Is the model considering f0(=pitch)?
|
||||
- f0: consider
|
||||
- nof0: don't consider
|
||||
2. Sampling rate used to train the model
|
||||
3. Number of feature channels used by the model
|
||||
4. Clients used for learning
|
||||
- org: This is the model trained in [orginal-RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI).
|
||||
- webui: The model trained on [ddPn08-RVC](https://github.com/ddPn08/rvc-webui).
|
||||
|
||||
## Model Setting
|
||||
|
||||
### Model Uploader
|
||||
|
||||
If enable PyTorch is turned on, you can select the PyTorch model (extension is pth). If you turn this on when using a model converted from RVC, the PyTorch item will appear. （From the next version, you can only choose either PyTorch or ONNX for each slot.
|
||||
You can choose either PyTorch or ONNX for each slot.
|
||||
|
||||
#### Model Slot
|
||||
|
||||
You can choose which frame to set the model in. The set model can be switched with Switch Model in Server Control.
|
||||
|
||||
#### Onnx(.onnx)
|
||||
#### Model(.onnx or .pth)
|
||||
Specify the trained model here. Required fields.
|
||||
You can choose either ONNX format (.onnx) or PyTorch format (.pth).
|
||||
|
||||
Specify the model in .onnx format here. This or PyTorch (.pth) is required.
|
||||
|
||||
#### PyTorch(.pth)
|
||||
|
||||
Specify the model in .pth format here. This or Onnx (.onnx) is required.
|
||||
If you trained with RVC-WebUI, it's in `/logs/weights`.
|
||||
- If trained with [orginal-RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI), it is in `/logs/weights`.
|
||||
- If trained with [ddPn08-RVC](https://github.com/ddPn08/rvc-webui), it is in `/models/checkpoints`.
|
||||
|
||||
#### feature(.npy)
|
||||
|
||||
This is an additional function that brings the features extracted by HuBERT closer to the training data. Used in pairs with index(.index).
|
||||
If you trained with RVC-WebUI, it is saved as `/logs/weights/total_fea.npy`.
|
||||
|
||||
- If trained with [orginal-RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI), it is in `/logs/your-expetiment-name/total_fea.npy`.
|
||||
- If trained with [ddPn08-RVC](https://github.com/ddPn08/rvc-webui), it is in `/models/checkpoints/your-model-name_index/your-model-name.0.big.npy`.
|
||||
|
||||
#### index(.index)
|
||||
|
||||
This is an additional function that brings the features extracted by HuBERT closer to the training data. Used in pairs with feature(.npy).
|
||||
If you trained with RVC-WebUI, it is saved as `/logs/weights/add_XXX.index`.
|
||||
|
||||
- If trained with [orginal-RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI), it is in `/logs/your-expetiment-name/total_fea.npy`.
|
||||
- If trained with [ddPn08-RVC](https://github.com/ddPn08/rvc-webui), it is in `/models/checkpoints/your-model-name_index/your-model-name.0.big.npy`.
|
||||
|
||||
#### half-precision
|
||||
|
||||
@ -82,7 +82,7 @@ ONNXモデルを出力します。PyTorchのモデルをONNXモデルに変換
|
||||
|
||||
## Model Setting
|
||||
### Model Uploader
|
||||
enable PyTorchをオンにするとPyTorchのモデル(拡張子がpth)を選ぶことができます。RVCから変換したモデルを使うときはこちらをオンにすると、PyTorchの項目がでてきます。次のバージョンからSlot毎にPyTorchかONNXのどちらかしか選べなくなります。
|
||||
Slot毎にPyTorchかONNXのどちらかのみ選べます。
|
||||
|
||||
#### Model Slot
|
||||
モデルをどの枠にセットするか選べます。セットしたモデルはServer ControlのSwitch Modelで切り替えられます。
|
||||
@ -91,18 +91,20 @@ enable PyTorchをオンにするとPyTorchのモデル(拡張子がpth)を選ぶ
|
||||
学習済みモデルをここで指定します。必須項目です。
|
||||
ONNX形式(.onnx)かPyTorch形式(.pth)のいずれかを選択可能です。
|
||||
|
||||
本家RVCで学習させた場合、`/logs/weights`に入っています。
|
||||
ddPn08RVCで学習させた場合、`/models/checkpoints`に入っています。
|
||||
- [orginal-RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)で学習させた場合、`/logs/weights`に入っています。
|
||||
- [ddPn08RVC](https://github.com/ddPn08/rvc-webui)で学習させた場合、`/models/checkpoints`に入っています。
|
||||
|
||||
#### feature(.npy)
|
||||
HuBERTで抽出した特徴を訓練データに近づける追加機能です。index(.index)とペアで使用します。
|
||||
本家RVCで学習させた場合、`/logs/実験名/total_fea.npy`という名前で保存されています。(2023/04/26にtotal_fea.npyを省略するアップデートが入ったので今後不要になる可能性があります)
|
||||
ddPn08RVCで学習させた場合、`/models/checkpoints/モデル名_index/モデル名.0.big.npy`という名前で保存されています。
|
||||
|
||||
- [orginal-RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)で学習させた場合、`/logs/実験名/total_fea.npy`という名前で保存されています。(2023/04/26にtotal_fea.npyを省略するアップデートが入ったので今後不要になる可能性があります)
|
||||
- [ddPn08RVC](https://github.com/ddPn08/rvc-webui)で学習させた場合、`/models/checkpoints/モデル名_index/モデル名.0.big.npy`という名前で保存されています。
|
||||
|
||||
#### index(.index)
|
||||
HuBERTで抽出した特徴を訓練データに近づける追加機能です。feature(.npy)とペアで使用します。
|
||||
本家RVCで学習させた場合、`/logs/実験名/add_XXX.index`という名前で保存されています。
|
||||
ddPn08RVCで学習させた場合、`/models/checkpoints/モデル名_index/モデル名.0.index`という名前で保存されています。
|
||||
|
||||
- [orginal-RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)で学習させた場合、`/logs/実験名/add_XXX.index`という名前で保存されています。
|
||||
- [ddPn08RVC](https://github.com/ddPn08/rvc-webui)で学習させた場合、`/models/checkpoints/モデル名_index/モデル名.0.index`という名前で保存されています。
|
||||
|
||||
#### half-precision
|
||||
精度をfloat32かfloat16のどちらで推論するか選べます。
|
||||
|
||||
Loading…
Reference in New Issue
Block a user