Update README.md of svc

1. Fixed the provided demo commands
2. Added the guide of vocoder downloading.

README.md

@@ -33,21 +33,27 @@ git lfs install
 git clone https://huggingface.co/amphion/singing_voice_conversion
 ```
 
-### Step2: Clone the Amphion's Source Code of GitHub
+### Step2: Download the vocoder checkpoint
+```bash
+git clone https://huggingface.co/amphion/BigVGAN_singing_bigdata
+```
+
+### Step3: Clone the Amphion's Source Code of GitHub
 ```bash
 git clone https://github.com/open-mmlab/Amphion.git
 ```
 
-### Step3: Specify the checkpoint's path
+### Step4: Specify the checkpoints' path
 Use the soft link to specify the downloaded checkpoint in first step:
 
 ```bash
 cd Amphion
-mkdir ckpts/svc
-ln -s ../singing_voice_conversion/vocalist_l1_contentvec+whisper ckpts/svc/vocalist_l1_contentvec+whisper
+mkdir -p ckpts/svc
+ln -s "$(realpath ../singing_voice_conversion/vocalist_l1_contentvec+whisper)" ckpts/svc/vocalist_l1_contentvec+whisper
+ln -s "$(realpath ../BigVGAN_singing_bigdata/bigvgan_singing)" pretrained/bigvgan_singing
 ```
 
-### Step4: Conversion
+### Step5: Conversion
 
 You can follow [this recipe](https://github.com/open-mmlab/Amphion/tree/main/egs/svc/MultipleContentsSVC#4-inferenceconversion) to conduct the conversion. For example, if you want to make Taylor Swift sing the songs in the `[Your Audios Folder]`, just run:
 
@@ -57,6 +63,7 @@ sh egs/svc/MultipleContentsSVC/run.sh --stage 3 --gpu "0" \
 	--infer_expt_dir "ckpts/svc/vocalist_l1_contentvec+whisper" \
 	--infer_output_dir "ckpts/svc/vocalist_l1_contentvec+whisper/result" \
 	--infer_source_audio_dir [Your Audios Folder] \
+    --infer_vocoder_dir "pretrained/bigvgan_singing" \
 	--infer_target_speaker "vocalist_l1_TaylorSwift" \
 	--infer_key_shift "autoshift"
 ```