โ† All examples

ModelEthio-ASR Amharic (600M)2Ethio-ASR Multi (300M)6Ethio-ASR Multi (600M)6Ethio-ASR Multi (94M)7Meta MMS-1B10OmniASR-CTC (1B)4OmniASR-CTC (300M)2OmniASR-CTC (3B)2OmniASR-LLM (1B)2OmniASR-LLM (300M)6OmniASR-LLM (3B)2OpenAI Whisper-small15
Audio qualityClean Studio2Ambient Room Noise2Harsh Environment4Distant / Low-Volume Mic1Wideband Phone (VoLTE)4Randomized Phone Channel4Narrowband 2G + Packet Loss8

What did the model get wrong?

OmniASR-LLM (1B) Clean Studio   Example 12 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Clean Studio
Clear, studio-quality recording. Best-case audio.
โœ… What was actually said
แŠ แˆแŠ• แ‹ซแˆˆแˆแ‰ต แŠ แ‹ณแˆ› แАแ‹ แ‹ˆแ‹ฐ แŒ…แ‰กแ‰ฒ แˆˆแˆตแˆซ แˆแˆ„แ‹ต แˆตแˆˆแˆ†แА แАแ‹
๐Ÿค– What this model heard
แŠ แˆแŠ• แ‹ซแˆˆแˆแ‰ต แŠ แ‹ณแˆ› แАแ‹ แ‹ˆแ‹ฐ แŒ…แ‰กแ‰ฒ แˆˆแˆตแˆซ แˆˆ แˆ„แ‹ต แˆตแˆˆแˆ†แА แАแ‹
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
9
Correct
1
Wrong
0
Missed
1
Extra
90%
Words right
Out of 10 spoken words, this model got 9 right (90%). Errors: 1 word wrong; 1 extra.

Try switching Audio quality โ€” see the same model degrade as the audio gets noisier.