Fact · Transcription
100.7percent word error rate
On the Fleurs benchmark, the Whisper large-v2 model had a word error rate of 100.7 percent for Malayalam.
Checked against its source on October 17, 2026
In the source's own words
“Model Lingala Lao Lithuanian Latvian Maori Macedonian Malayalam Mongolian Marathi Malay ... Whisper large-v2 75.6 101.5 28.1 23.1 38.5 16.5 100.7 110.5 38.3 8.7”
Robust Speech Recognition via Large-Scale Weak Supervision (full text), Alec Radford et al., OpenAI (arXiv), 2022, Table 13 (Fleurs), column Malayalam.
Open the original (DOI 10.48550/arXiv.2212.04356)- What it measures
- Fleurs is a read-speech benchmark in about 100 languages. The figure is for the largest Whisper model in the table, large-v2, from 2022.
- What it does not show
- A value above 100 percent means more wrong words than reference words, usually from inserted words. Read sentences, not conversation.