BuzzASR Persian
Persian speech recognition with BuzzASR (Whisper-large-v3)
Automatic Speech Recognition, Supervised Fine-Tuning, 102 Language Support
One specialist model per language. BuzzASR is a suite of 102 monolingual ASR models, each a fine-tune of Whisper-large-v3 specialized to a single language.
Accepted at EMNLP 2026 · Shivam Singh, Aditya Yadavalli, Catherine Arnett, Alex Warstadt · LeMN Lab, UC San Diego in collaboration with EleutherAI
Big multilingual models spread themselves thin across hundreds of languages. We asked whether a single specialist, the same size as Whisper, could beat the giant generalists. In most languages, it can.
Combined FLEURS + Common Voice, normalized CER %
| Language | BuzzASR CER | Whisper zero-shot | Note |
|---|---|---|---|
| Cantonese | 13.0 | 36.4 | SOTA, 2x better than the next-best system |
| Punjabi | 8.8 | 42.3 | SOTA |
| Mongolian | 5.2 | 38.2 | SOTA |
| Korean | 4.6 | 5.7 | SOTA, independently re-scored |
| Amharic | 9.1 | 191 | >20x reduction over Whisper |
We ran the full FLEURS test sets through Whisper-large-v3-turbo on Cloudflare Workers AI and through BuzzASR (CER %, lower is better):
| Language | Workers AI turbo | BuzzASR |
|---|---|---|
| Amharic | 97.9 | 11.5 |
| Sorani Kurdish* | 71.4 | 12.8 |
| Maltese | 21.0 | 5.1 |
| Estonian | 3.4 | 2.9 |
| Hungarian | 3.5 | 3.2 |
*Whisper has no Sorani option, so turbo had to detect the language.
Browse all 102 models in the Models tab above, or go to huggingface.co/BuzzASR/<language>.
from transformers import pipeline
asr = pipeline("automatic-speech-recognition", model="BuzzASR/mongolian")
print(asr("audio.wav")["text"])
The language and task prompt is built into each model, so there's nothing else to set.