← All examples

ModelEthio-ASR Amharic (600M)3Ethio-ASR Multi (300M)15Ethio-ASR Multi (600M)3Ethio-ASR Multi (94M)5Meta MMS-1B7OmniASR-CTC (1B)7OmniASR-CTC (300M)7OmniASR-CTC (3B)7OmniASR-LLM (1B)2OmniASR-LLM (300M)6OmniASR-LLM (3B)5OpenAI Whisper-small21
Audio qualityClean Studio1Ambient Room Noise1Harsh Environment1Distant / Low-Volume Mic1Wideband Phone (VoLTE)1Randomized Phone Channel1Narrowband 2G + Packet Loss5

What did the model get wrong?

OmniASR-LLM (3B) Narrowband 2G + Packet Loss   Example 3 of 20  ·  speaker: Female

🎧 Listen — Narrowband 2G + Packet Loss
Heavy background noise plus phone-call compression — worst-case stress test.
✅ What was actually said
በስልክ ደውየ ማግኘት የምችልበት የጥሪ ማእከል አለ
🤖 What this model heard
በስልክ ደብ እዚህ ማግኘት የምትችልበት የጥሪ ማእከላሉ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
3
Correct
3
Wrong
1
Missed
1
Extra
43%
Words right
Out of 7 spoken words, this model got 3 right (43%). Errors: 3 words wrong; 1 missed; 1 extra.

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