โ† All examples

ModelEthio-ASR Amharic (600M)1Ethio-ASR Multi (300M)15Ethio-ASR Multi (600M)7Ethio-ASR Multi (94M)7Meta MMS-1B8OmniASR-CTC (1B)8OmniASR-CTC (300M)7OmniASR-CTC (3B)7OmniASR-LLM (1B)1OmniASR-LLM (300M)4OmniASR-LLM (3B)7OpenAI Whisper-small13
Audio qualityClean Studio15Ambient Room Noise13Harsh Environment13Distant / Low-Volume Mic15Wideband Phone (VoLTE)11Randomized Phone Channel16Narrowband 2G + Packet Loss13

What did the model get wrong?

OpenAI Whisper-small Narrowband 2G + Packet Loss   Example 11 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
แŠฅแˆฝ แ‰ แŒฃแˆ แŠจแแ‰ฐแŠ›แ‹ แแŒฅแŠแ‰ต แŠฅแˆตแŠจ แˆตแŠ•แ‰ต แ‹ญแ‹ฐแˆญแˆณแˆ แ‹‹แŒ‹แ‹แˆต
๐Ÿค– What this model heard
but i m custom off the next cutting to that part well guys
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
8
Wrong
0
Missed
5
Extra
0%
Words right
Out of 8 spoken words, this model got 0 right (0%). Errors: 8 words wrong; 5 extra.

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