# Falcon ASR speech model released for Arabic and four other languages

> Hugging Face unveils a 1.6 B‑parameter model that lowers Arabic word error rate to 20.9% and supports English, French, Spanish and Portuguese.

Oossa · 2026-10-07 · https://oossa.com/en/falcon-asr-speech-model-released-for-arabic-and-four-other-languages

Hugging Face has launched Falcon‑ASR, a 1.6 billion‑parameter speech‑recognition model built by the Technology Innovation Institute in Abu Dhabi. It targets Arabic, especially the Emirati dialect, and also transcribes English, French, Spanish and Portuguese. In the Open Universal Arabic ASR Leaderboard the model achieved an average word error rate (WER) of 20.92%, beating the previous best published score of 23.17%.

## The facts

- Parameters: 1.6 B
- Average Arabic WER: 20.92% (vs 23.17% previous best)

## Why it matters

Arabic speakers, particularly in the UAE, can now get more accurate automated transcriptions for meetings and calls.

## Sources & references

1. [Introducing Falcon ASR](https://huggingface.co/blog/tiiuae/falcon-asr) – Hugging Face, 2026-10-07

Last updated: 2026-10-07
