18 May 2026
FFASR Leaderboard Early Access
Be among the first to submit and evaluate ASR models, and play a role in influencing how the FFASR leaderboard on Hugging Face is built.
What is FFASR
A leaderboard built for real deployment
Most ASR benchmarks are recorded close to the microphone in clean conditions.
That does not reflect how systems behave in meeting rooms, smart speakers, or hands-free devices.
FFASR evaluates models across five far-field categories using high-fidelity acoustic simulations, exposing performance differences that remain hidden in traditional benchmarks.
Why it matters
Your model does not ship into a lab
FFASR gives you:
- A transparent view of robustness across acoustic conditions
- Reproducible evaluation at scale
- A way to compare models under realistic constraints
You can submit Hugging Face models and see exactly where they succeed or fail.
Recent posts
Treble Technologies, a world leader in sound simulation and synthetic acoustic data generation, today announced that it has raised $18 million (approximately €15M) in its Series A-2 round to expand its innovative technology platform for enabling better and easier-to-develop audio-enabled systems. Paladin Capital Group led the round, with participation from existing investors KOMPAS VC, Frumtak Ventures, and the European Innovation Council (EIC) Fund. The latest round brings Treble’s total funding to date to €36M.
Introducing FFASR Leaderboard with Hugging Face
Sign up for the on-demand webinar celebrating the launch of the Far Field ASR Leaderboard (FFASR) on Hugging Face, a new benchmark designed to move audio AI evaluation beyond near field assumptions.
The launch of the Far-Field ASR Leaderboard
Treble Technologies and Hugging Face address voice AI’s unspoken dilemma with groundbreaking benchmark of ASR models
