โ† All examples

ModelEthio-ASR Amharic (600M)0Ethio-ASR Multi (300M)1Ethio-ASR Multi (600M)1Ethio-ASR Multi (94M)2Meta MMS-1B7OmniASR-CTC (1B)5OmniASR-CTC (300M)3OmniASR-CTC (3B)1OmniASR-LLM (1B)1OmniASR-LLM (300M)2OmniASR-LLM (3B)1OpenAI Whisper-small19
Audio qualityClean Studio0Ambient Room Noise0Harsh Environment0Distant / Low-Volume Mic0Wideband Phone (VoLTE)1Randomized Phone Channel2Narrowband 2G + Packet Loss3

What did the model get wrong?

Ethio-ASR Amharic (600M) Harsh Environment   Example 3 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Harsh Environment
Very heavy background noise โ€” much harder than typical audio.
โœ… What was actually said
แ‰ แˆตแˆแŠญ แ‹ฐแ‹แ‹จ แˆ›แŒแŠ˜แ‰ต แ‹จแˆแ‰ฝแˆแ‰ แ‰ต แ‹จแŒฅแˆช แˆ›แŠฅแŠจแˆ แŠ แˆˆ
๐Ÿค– What this model heard
แ‰ แˆตแˆแŠญ แ‹ฐแ‹แ‹จ แˆ›แŒแŠ˜แ‰ต แ‹จแˆแ‰ฝแˆแ‰ แ‰ต แ‹จแŒฅแˆช แˆ›แŠฅแŠจแˆ แŠ แˆˆ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
7
Correct
0
Wrong
0
Missed
0
Extra
100%
Words right
Out of 7 spoken words, this model got 7 right (100%). Errors: everything correct.

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