Updating BIRB benchmark portion of README.

PiperOrigin-RevId: 590221321

README.md

@@ -41,8 +41,9 @@ After building the container, to run the unit tests, use:
 docker run --rm -t perch python -m unittest discover -s chirp/tests -p "*test.py"
 ```
 
-## BIRB data preparation
+## BIRB benchmark
 
+### Data preparation
 To build the BIRB evaluation data, after [installing](#installation) the `chirp` package, run the following command from the repository's root directory:
 
 ```bash
@@ -53,4 +54,7 @@ poetry run tfds build -i chirp.data.bird_taxonomy,chirp.data.soundscapes \
 
 The process should take 36 to 48 hours to complete and use around 256 GiB of disk space.
 
+### Benchmark README
+For details on setting up the benchmark and evaluation protocol, please refer to this [brief readme](https://docs.google.com/document/d/1RasVkxIKKlUToFlJ8gZxaHqIE-mMy9G1MZwfK98Gb-I) with instructions. The evaluation codebase is in [perch/chirp/eval](https://github.com/google-research/perch/tree/main/chirp/eval).
+
 *This is not an officially supported Google product.*