Update README.md

README.md

@@ -40,18 +40,38 @@ for more information.
 ### Training Data
 
 <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-All of the training data is extracted from the Windows client of Uma Musume: Pretty Derby using the [umamusume-voice-text-extractor](https://github.com/chinosk6/umamusume-voice-text-extractor)
-The copyright of the training dataset belongs to Cygames.
-Only the voice is used, the live music soundtrack is not included in the training dataset.
+All of the training data is extracted from the Windows client of Uma Musume: Pretty Derby using the [umamusume-voice-text-extractor](https://github.com/chinosk6/umamusume-voice-text-extractor).  
+The copyright of the training dataset belongs to Cygames.  
+Only the voice is used, the live music soundtrack is not included in the training dataset.  
 
 
 ### Training Procedure 
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
+#### Training Environment Preparation
+- Download the base models mentioned in  [the README.md file of the *so-vits-svc project*](https://github.com/svc-develop-team/so-vits-svc/blob/4.1-Stable/README.md).  
+*You should download [checkpoint_best_legacy_500.pt](https://github.com/svc-develop-team/so-vits-svc/blob/4.1-Stable/README.md#1-if-using-contentvec-as-speech-encoderrecommended)
+, [D_0.pth, G_0.pth](https://huggingface.co/OOPPEENN/so-vits-svc-4.0-pretrained-models/resolve/main/vec768l12_vol_tiny.7z)(for sovits model), [model_0.pt](https://github.com/CNChTu/Diffusion-SVC/blob/Stable/README_en.md#21-pre-training-diffusion-model-which-training-full-depth)(for shallow diffusion)
+, [rmvpe.pt](https://github.com/svc-develop-team/so-vits-svc/blob/4.1-Stable/README.md#rmvpe)(for the f0 predictor RMVPE), [model](https://github.com/svc-develop-team/so-vits-svc/blob/4.1-Stable/README.md#nsf-hifigan)(for NSF_hifigan).*  
+- Place checkpoint_best_legacy_500.pt, rmvpe.pt in .\pretrain, place model and its config.json in .\pretrain\nsf_hifigan, place D_0.pth, G_0.pth in .\logs\44k, place model_0.pt in .\logs\44k\diffusion .  
+  Credits: The D_0.pth and G_0.pth provided above is from [OOPPEENN](https://huggingface.co/OOPPEENN/so-vits-svc-4.0-pretrained-models).
+
 #### Preprocessing
 
-Navigate to the directory of "so-vits-svc" and execute `python resample.py --skip_loudnorm` .
+- Delete all WAV files smaller than 400KB, and copy them to .\dataset_raw\AgnesTachyon
+- Navigate to the directory of "so-vits-svc" and execute `python resample.py --skip_loudnorm` .
+- Execute `python preprocess_flist_config.py --speech_encoder vec768l12 --vol_aug` .
+- Edit the parameters in config.json and diffusion.yaml.
+- Execute `python preprocess_hubert_f0.py --f0_predictor rmvpe --use_diff`
+
+#### Training
+- Execute `python train.py -c configs/config.json -m 44k` .  
+##### [Optional]  
+- Execute `python train_diff.py -c configs/diffusion.yaml` to train the shallow diffusion model.  
+- Execute `python cluster/train_cluster.py --gpu` to train the cluster model.  
+- Execute `python train_index.py -c configs/config.json` to train the feature index model.  
+
 
 #### Training Hyperparameters