update readme

README.md

@@ -132,13 +132,13 @@ Upload a reference audio. The model clones the timbre, and you can still use con
 ```python
 wav = model.generate(
     text="This is a cloned voice generated by VoxCPM2.",
-    reference_wav_path="speaker.wav",
+    reference_wav_path="path/to/voice.wav",
 )
 sf.write("clone.wav", wav, model.tts_model.sample_rate)
 
 wav = model.generate(
     text="(slightly faster, cheerful tone)This is a cloned voice with style control.",
-    reference_wav_path="speaker.wav",
+    reference_wav_path="path/to/voice.wav",
     cfg_value=2.0,
     inference_timesteps=10,
 )
@@ -152,9 +152,9 @@ Provide both the reference audio and its exact transcript for audio-continuation
 ```python
 wav = model.generate(
     text="This is an ultimate cloning demonstration using VoxCPM2.",
-    prompt_wav_path="speaker_reference.wav",
+    prompt_wav_path="path/to/voice.wav",
     prompt_text="The transcript of the reference audio.",
-    reference_wav_path="speaker_reference.wav",
+    reference_wav_path="path/to/voice.wav", # optional, for better simliarity 
 )
 sf.write("hifi_clone.wav", wav, model.tts_model.sample_rate)
 ```
@@ -200,6 +200,7 @@ voxcpm clone \
   --text "This is a voice cloning demo." \
   --prompt-audio path/to/voice.wav \
   --prompt-text "reference transcript" \
+  --reference-audio path/to/voice.wav \ # optional, for better simliarity
   --output out.wav
 
 # Batch processing