โ† All examples

ModelEthio-ASR Amharic (600M)8Ethio-ASR Multi (300M)18Ethio-ASR Multi (600M)9Ethio-ASR Multi (94M)9Meta MMS-1B9OmniASR-CTC (1B)9OmniASR-CTC (300M)8OmniASR-CTC (3B)4OmniASR-LLM (1B)8OmniASR-LLM (300M)8OmniASR-LLM (3B)9OpenAI Whisper-small9
Audio qualityClean Studio1Ambient Room Noise1Harsh Environment1Distant / Low-Volume Mic1Wideband Phone (VoLTE)1Randomized Phone Channel1Narrowband 2G + Packet Loss8

What did the model get wrong?

Ethio-ASR Amharic (600M) Narrowband 2G + Packet Loss   Example 7 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Narrowband 2G + Packet Loss
Heavy background noise plus phone-call compression โ€” worst-case stress test.
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‰ฐแŠแ‰ต แŒฅแ‰…แˆแŠฌแ‰ฝ แˆ˜แŒแ‹›แ‰ต แŠฅแŠ•แ‰ฝแˆ‹แˆ‰ แŒˆแŒ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
1
Correct
4
Wrong
4
Missed
0
Extra
11%
Words right
Out of 9 spoken words, this model got 1 right (11%). Errors: 4 words wrong; 4 missed.

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