---
license: cc-by-4.0
library_name: pytorch
base_model: facebook/sam-audio-small
tags:
  - audio-source-separation
  - audio
  - pytorch
  - transfer-dit
  - sam-audio
---

# Learning2HearWhileWalking

This repository provides Transfer-DiT checkpoints for ego-noise separation in
the Learning2HearWhileWalking project.

## Checkpoints

| Robot | File |
|---|---|
| G1 | `checkpoints/G1/best.pt` |
| Go1 | `checkpoints/Go1/best.pt` |

## Code

The Transfer-DiT implementation is available at:

https://github.com/blind-review-demo/Learning2HearWhileWalking

SAM-Audio code and base model weights are not included in this repository.
Install SAM-Audio and download the base model as described in the code
repository.

## Usage

```bash
git clone https://github.com/blind-review-demo/Learning2HearWhileWalking
cd Learning2HearWhileWalking
bash scripts/setup_sam_audio.sh
huggingface-cli login
python scripts/download_sam_audio_weights.py --model-id facebook/sam-audio-small
python scripts/separate_audio.py \
  --audio path/to/mixed.wav \
  --checkpoint path/to/best.pt \
  --out-dir outputs/demo
```

## Files

SHA256 checksums are provided in `SHA256SUMS`.