← All examples

ModelEthio-ASR Amharic (600M)11Ethio-ASR Multi (300M)14Ethio-ASR Multi (600M)9Ethio-ASR Multi (94M)6Meta MMS-1B19OmniASR-CTC (1B)0OmniASR-CTC (300M)0OmniASR-CTC (3B)6OmniASR-LLM (1B)0OmniASR-LLM (300M)1OmniASR-LLM (3B)0OpenAI Whisper-small219
Audio qualityClean Studio8Ambient Room Noise8Harsh Environment14Distant / Low-Volume Mic8Wideband Phone (VoLTE)16Randomized Phone Channel13Narrowband 2G + Packet Loss19

What did the model get wrong?

Ethio-ASR Multi (300M) Harsh Environment   Example 1 of 20  ·  speaker: Female

🎧 Listen — Harsh Environment
Very heavy background noise — much harder than typical audio.
✅ What was actually said
ሲ ሲ ቲ ሁለት ዜሮ ሁለት አምስት አንድ ሁለት አንድ ሰባት ሁለት አራት ሰባት ስምንት ዜሮ ሰባት ዘጠኝ አራት
🤖 What this model heard
tir ሲ c ቲ ሁለትለት ዜro ሁለትuለት ም ን ሁለትለት አንድ ሰባት ሁለትu አራትት ሰባት ስን ዜr ሰባት ዘዘጠኝኛ ራት
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
6
Correct
13
Wrong
0
Missed
1
Extra
32%
Words right
Out of 19 spoken words, this model got 6 right (32%). Errors: 13 words wrong; 1 extra.

Try switching Audio quality — see the same model degrade as the audio gets noisier.