Update README.md

README.md

@@ -11,6 +11,25 @@ Demo of audio restorations: [VoiceRestore](https://sparkling-rabanadas-3082be.ne
 
 Credits: This repository is based on the [E2-TTS implementation by Lucidrains](https://github.com/lucidrains/e2-tts-pytorch)
 
+## Usage
+``` bash
+!git lfs install
+!git clone https://huggingface.co/jadechoghari/VoiceRestore
+%cd VoiceRestore
+!pip install -r requirements.txt
+```
+
+``` python
+from transformers import AutoModel
+# path to the model folder (on colab it's as follows)
+checkpoint_path = "/content/VoiceRestore"
+model = AutoModel.from_pretrained(checkpoint_path, trust_remote_code=True)
+model("test_input.wav", "test_output.wav")
+```
+
+
+
+
 ## Example
 ### Degraded Input: 
 
@@ -44,48 +63,6 @@ https://github.com/user-attachments/assets/fdbbb988-9bd2-4750-bddd-32bd5153d254
 - **Pretrained Model**: Includes a 301 million parameter transformer model with pre-trained weights. (Model is still in the process of training, there will be further checkpoint updates)
 
 ---
-## Quick Start
-
-1. Clone the repository:
-   ```bash
-   git clone --recurse-submodules https://github.com/skirdey/voicerestore.git
-   cd VoiceRestore
-   ```
-
-   if you did not clone with `--recurse-submodules`, you can run:
-   ```bash
-   git submodule update --init --recursive
-   ```
-
-2. Install dependencies:
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Download the [pre-trained model](https://drive.google.com/drive/folders/1uBJNp4mrPJQY9WEaiTI9u09IsRg1lAPR?usp=sharing) and place it in the `checkpoints` folder.
-
-4. Run a test restoration:
-   ```bash
-   python inference_short.py --checkpoint ./checkpoints/voice-restore-20d-16h-optim.pt --input test_input.wav --output test_output.wav --steps 32 --cfg_strength 0.5
-   ```
-   This will process `test_input.wav` and save the result as `test_output.wav`.
-
-5. Run a long form restoration, it uses window chunking:
-   ```bash
-   python inference_long.py --checkpoint ./checkpoints/voice-restore-20d-16h-optim.pt --input test_input_long.wav --output test_output_long.wav --steps 32 --cfg_strength 0.5 --window_size_sec 10.0 --overlap 0.25
-   ```
-   This will process `test_input_long.wav` (you need to provide it) and save the result as `test_output_long.wav`.
-
-## Usage
-
-To restore your own audio files:
-
-```python
-from model import OptimizedAudioRestorationModel
-
-model = OptimizedAudioRestorationModel()
-restored_audio = model.forward(input_audio, steps=32, cfg_strength=0.5)
-```