Upload folder using huggingface_hub

checkpoints/README.md

@@ -6,21 +6,30 @@ All inference checkpoints should be placed under `open_source_release/checkpoint
 checkpoints/
   stage1_knnvc/
     hifigan/
-      g_00125000.pt                  # optional custom checkpoint
+      g_00125000.pt                  # required for stage1
     wavlm/
-      WavLM-Large.pt
+      WavLM-Large.pt                 # required for stage1
   stage2_sovits/
     chkpt/
       sovits5.0_all_nocross/*.pt     # default non-cross inference
-      sovits5.0_all/*.pt             # optional cross-mode inference
+      sovits5.0_all_cross/*.pt       # cross-mode path in code
     whisper_pretrain/
       large-v2.pt
     hubert_pretrain/
       hubert-soft-0d54a1f4.pt
     crepe/assets/
       full.pth
+    speaker_pretrain/
+      best_model.pth.tar             
+    vits_pretrain/
+      sovits5.0.pretrain.pth         
 ```
 
+Notes:
+
+1. If your cross checkpoint directory is `sovits5.0_all_cross/`, pass it explicitly with `--model` (`stage2`) or `--stage2-model` (`pipeline`).
+2. `speaker_pretrain/best_model.pth.tar` is used by `build-spk`; it is not required when you already have ready-made `.spk.npy` files.
+
 For attribution and citation notes, see:
 
 - `THIRD_PARTY_NOTICES.md`