← All examples

ModelEthio-ASR Amharic (600M)4Ethio-ASR Multi (300M)8Ethio-ASR Multi (600M)5Ethio-ASR Multi (94M)7Meta MMS-1B12OmniASR-CTC (1B)7OmniASR-CTC (300M)8OmniASR-CTC (3B)3OmniASR-LLM (1B)7OmniASR-LLM (300M)0OmniASR-LLM (3B)0OpenAI Whisper-small12
Audio qualityClean Studio3Ambient Room Noise1Harsh Environment1Distant / Low-Volume Mic1Wideband Phone (VoLTE)1Randomized Phone Channel1Narrowband 2G + Packet Loss4

What did the model get wrong?

OmniASR-CTC (3B) Clean Studio   Example 9 of 20  Âˇ  speaker: Female

🎧 Listen — Clean Studio
Clear, studio-quality recording. Best-case audio.
✅ What was actually said
ቁጥሩ ዜሮ ዘጠኝ አንድ ሁለት አምስት ስድስት ሰባት ስምንት ዘጠኝ ዜሮ ነው
🤖 What this model heard
ቁጥሩ ዜሮሮ ዘጠኝ አንድ ሁለት አምስት ስድስት ሰባት ስምንትንት ዘጠኝ ዜሮሮ ነው
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
9
Correct
3
Wrong
0
Missed
0
Extra
75%
Words right
Out of 12 spoken words, this model got 9 right (75%). Errors: 3 words wrong.

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