diff --git a/README.md b/README.md
index 66e1ffd..1ad133e 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@
CLAP (Contrastive Language-Audio Pretraining) is a model that learns acoustic concepts from natural language supervision and enables “Zero-Shot” inference. The model has been extensively evaluated in 26 audio downstream tasks achieving SoTA in several of them including classification, retrieval, and captioning.
-
+
## Setup
@@ -20,8 +20,6 @@ pip install git+https://github.com/microsoft/CLAP.git
## Usage
-In `CLAP\src\`:
-
- Zero-Shot Classification and Retrieval
```python
from msclap import CLAP
@@ -57,7 +55,7 @@ Take a look at [examples](./examples/) for usage examples.
To run Zero-Shot Classification on the ESC50 dataset try the following:
```bash
-> cd src && python zero_shot_classification.py
+> cd examples && python zero_shot_classification.py
```
Output (version 2023)
```bash
diff --git a/docs/clap2_diagram.png b/docs/clap2_diagram.png
new file mode 100644
index 0000000..606f131
Binary files /dev/null and b/docs/clap2_diagram.png differ