← All examples

ModelEthio-ASR Amharic (600M)8Ethio-ASR Multi (300M)17Ethio-ASR Multi (600M)10Ethio-ASR Multi (94M)12Meta MMS-1B13OmniASR-CTC (1B)2OmniASR-CTC (300M)5OmniASR-CTC (3B)0OmniASR-LLM (1B)0OmniASR-LLM (300M)2OmniASR-LLM (3B)2OpenAI Whisper-small13
Audio qualityClean Studio0Ambient Room Noise0Harsh Environment0Distant / Low-Volume Mic0Wideband Phone (VoLTE)0Randomized Phone Channel0Narrowband 2G + Packet Loss0

What did the model get wrong?

OmniASR-CTC (3B) Narrowband 2G + Packet Loss   Example 19 of 20  ·  speaker: Male

🎧 Listen — Narrowband 2G + Packet Loss
Heavy background noise plus phone-call compression — worst-case stress test.
✅ What was actually said
ቁጥሩ ሰባት ሶስት አንድ ዜሮ አንድ ሁለት ሰባት ዘጠኝ አምስት ዜሮ አራት ነው
🤖 What this model heard
ቁጥሩ ሰባት ሶስት አንድ ዜሮ አንድ ሁለት ሰባት ዘጠኝ አምስት ዜሮ አራት ነው
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
13
Correct
0
Wrong
0
Missed
0
Extra
100%
Words right
Out of 13 spoken words, this model got 13 right (100%). Errors: everything correct.

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