---
title: Persian ASR Double Benchmark
emoji: 🎙️
colorFrom: red
colorTo: pink
sdk: gradio
sdk_version: 5.22.0
app_file: app.py
python_version: 3.11
pinned: false
---

# Persian ASR Double Benchmark Leaderboard

A public leaderboard for comparing Persian speech recognition models on two complementary eval sets.

Benchmarks:

- `gold69`: 69 challenging Persian audio clips with curated references.
- `fleurs`: Persian FLEURS clips for a cleaner public reference point.

Metrics:

- WER and CER are normalized with the shared Persian normalizer from `eval_student_double.py`.
- Lower is better.