Update README.md

README.md

@@ -55,15 +55,15 @@ We use `torch.hub` to make loading the model easy -- no cloning of the repo need
 1. **Install pip dependencies**: we have 3 inference dependencies only `torch`, `torchaudio`, `librosa`, `vocos`, and `encodec`. Python must be at version 3.10 or greater, and torch must be v2.0 or greater.
 
 ```bash
-pip install --upgrade torch torchaudio librosa vocos encodec
+pip install --upgrade torch torchaudio librosa vocos encodec huggingface_hub
 ```
 
-2. **Load models**: load the Mars 5 AR and NAR model from torch hub:
+2. **Load models**: load the Mars 5 AR and NAR model from the huggingface hub:
 
 ```python
-import torch, librosa
-
-mars5, config_class = torch.hub.load('Camb-ai/mars5-tts', 'mars5_english', trust_repo=True)
+from inference import Mars5TTS, InferenceConfig as config_class
+import librosa
+mars5 = Mars5TTS.from_pretrained("CAMB-AI/MARS5-TTS")
 # The `mars5` contains the AR and NAR model, as well as inference code.
 # The `config_class` contains tunable inference config settings like temperature.
 ```