โ† All examples

ModelEthio-ASR Amharic (600M)8Ethio-ASR Multi (300M)17Ethio-ASR Multi (600M)10Ethio-ASR Multi (94M)12Meta MMS-1B13OmniASR-CTC (1B)2OmniASR-CTC (300M)5OmniASR-CTC (3B)0OmniASR-LLM (1B)0OmniASR-LLM (300M)2OmniASR-LLM (3B)2OpenAI Whisper-small13
Audio qualityClean Studio13Ambient Room Noise13Harsh Environment13Distant / Low-Volume Mic13Wideband Phone (VoLTE)13Randomized Phone Channel13Narrowband 2G + Packet Loss13

What did the model get wrong?

Meta MMS-1B Narrowband 2G + Packet Loss   Example 19 of 20  ยท  speaker: Male

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‰แŒฅแˆฉ แˆฐแ‰ฃแ‰ต แˆถแˆตแ‰ต แŠ แŠ•แ‹ต แ‹œแˆฎ แŠ แŠ•แ‹ต แˆแˆˆแ‰ต แˆฐแ‰ฃแ‰ต แ‹˜แŒ แŠ แŠ แˆแˆตแ‰ต แ‹œแˆฎ แŠ แˆซแ‰ต แАแ‹
๐Ÿค– What this model heard
แ‰  แ‰  แ‹ˆ แŠ“ แ‹ˆ แ‰ตแˆ˜
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
6
Wrong
7
Missed
0
Extra
0%
Words right
Out of 13 spoken words, this model got 0 right (0%). Errors: 6 words wrong; 7 missed.

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