Update README.md

README.md

@@ -19,6 +19,11 @@ tags:
 The model is a recreation of [3loi/SER-Odyssey-Baseline-WavLM-Multi-Attributes](https://huggingface.co/3loi/SER-Odyssey-Baseline-WavLM-Multi-Attributes) for direct implementation in torch, with class definition and feed forward method. This model was recreated with the hopes of greater flexibilty of control, training/fine-tuning of model. The model was trained on the same [MSP-Podcast](https://ecs.utdallas.edu/research/researchlabs/msp-lab/MSP-Podcast.html) dataset as the original, but a different smaller subset was used. The subset is evenly distributed across gender and emotion category with hopes that training would improve accuracy of valence and arousal predictions. 
 This model is therefore a multi-attributed based model which predict arousal, dominance and valence. However, unlike the original model, I just kept the original attribute score range of  0...7 (the range the dataset follows). I will provide the evaluations later on. For now I decided to make this repo so that other people could test out my model and see what they think of the inference accuracy themselves, or retrain from scratch, modify etc. My best trained weights s of now are provided in this repo. The class definition for the model is can be found in my [github](https://github.com/PhilipAmadasun/SER-Model-for-dimensional-attribute-prediction#).
 
+# Get class definition
+```
+git clone https://github.com/PhilipAmadasun/SER-Model-for-dimensional-attribute-prediction.git
+```
+
 # Usage
 ## Inference Testing
 ```python
@@ -37,7 +42,7 @@ model.load_state_dict(checkpoint['model_state_dict'])
 model.to(device)
 model.eval()
 
-audio_path = "wav file"
+audio_path = "<wav file>"
 audio, sr = torchaudio.load(audio_path)
 
 if sr != model.sample_rate:
@@ -206,7 +211,7 @@ if __name__ == "__main__":
     # -----------------------------------------
     device = "cuda" if torch.cuda.is_available() else "cpu"
     
-    checkpoint_path = "<weights.pt>""
+    checkpoint_path = "<weights.pt>"
     model = load_model_from_checkpoint(checkpoint_path, device=device)
     
     # Suppose you have a folder of .wav files