โ† All examples

ModelEthio-ASR Amharic (600M)1Ethio-ASR Multi (300M)4Ethio-ASR Multi (600M)2Ethio-ASR Multi (94M)3Meta MMS-1B9OmniASR-CTC (1B)4OmniASR-CTC (300M)2OmniASR-CTC (3B)2OmniASR-LLM (1B)0OmniASR-LLM (300M)1OmniASR-LLM (3B)0OpenAI Whisper-small13
Audio qualityClean Studio1Ambient Room Noise3Harsh Environment3Distant / Low-Volume Mic1Wideband Phone (VoLTE)4Randomized Phone Channel3Narrowband 2G + Packet Loss8

What did the model get wrong?

OmniASR-LLM (300M) Clean Studio   Example 7 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Clean Studio
Clear, studio-quality recording. Best-case audio.
โœ… What was actually said
แ‹จแŠขแŠ•แ‰ฐแˆญแŠ”แ‰ต แŒฅแ‰…แˆ แ‹ˆแ‹ญแˆ แ“แŠฌแŒ… แˆ˜แŒแ‹›แ‰ต แŠฅแ‰ฝแˆ‹แˆˆแˆ แ‹‹แŒ‹แ‹ แˆตแŠ•แ‰ต แŠแ‹
๐Ÿค– What this model heard
แ‹จแŠขแŠ•แ‰ฐแˆญแŠ”แ‰ต แŒฅแ‰…แˆ แ‹ˆแ‹ญแˆ แ“แŠชแ‰ฝ แˆ˜แŒแ‹›แ‰ต แŠฅแ‰ฝแˆ‹แˆˆแˆ แ‹‹แŒ‹แ‹ แˆตแŠ•แ‰ต แŠแ‹
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
8
Correct
1
Wrong
0
Missed
0
Extra
89%
Words right
Out of 9 spoken words, this model got 8 right (89%). Errors: 1 word wrong.

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