← All examples

ModelEthio-ASR Amharic (600M)4Ethio-ASR Multi (300M)3Ethio-ASR Multi (600M)6Ethio-ASR Multi (94M)3Meta MMS-1B12OmniASR-CTC (1B)0OmniASR-CTC (300M)1OmniASR-CTC (3B)0OmniASR-LLM (1B)1OmniASR-LLM (300M)0OmniASR-LLM (3B)0OpenAI Whisper-small12
Audio qualityClean Studio4Ambient Room Noise3Harsh Environment4Distant / Low-Volume Mic4Wideband Phone (VoLTE)5Randomized Phone Channel8Narrowband 2G + Packet Loss5

What did the model get wrong?

Ethio-ASR Amharic (600M) Harsh Environment   Example 5 of 20  ·  speaker: Male

🎧 Listen — Harsh Environment
Very heavy background noise — much harder than typical audio.
✅ What was actually said
ቁጥሬ ዜሮ ዘጠኝ ሰላሳ አራት አራት አምስት ስድስት ሰባት ስምንት ዘጠኝ ነው
🤖 What this model heard
ቁጥሬ ዘጠኝ ሰላሳ አራት አርባ አምስትም ስስ ሰባት ስምንት ዘጠኝ ነው
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
8
Correct
3
Wrong
1
Missed
0
Extra
67%
Words right
Out of 12 spoken words, this model got 8 right (67%). Errors: 3 words wrong; 1 missed.

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