โ† All examples

ModelEthio-ASR Amharic (600M)8Ethio-ASR Multi (300M)14Ethio-ASR Multi (600M)9Ethio-ASR Multi (94M)9Meta MMS-1B9OmniASR-CTC (1B)9OmniASR-CTC (300M)9OmniASR-CTC (3B)7OmniASR-LLM (1B)7OmniASR-LLM (300M)8OmniASR-LLM (3B)7OpenAI Whisper-small16
Audio qualityClean Studio0Ambient Room Noise0Harsh Environment3Distant / Low-Volume Mic0Wideband Phone (VoLTE)5Randomized Phone Channel2Narrowband 2G + Packet Loss7

What did the model get wrong?

OmniASR-CTC (3B) Narrowband 2G + Packet Loss   Example 6 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
แˆ˜แ‰ธ แŠแ‹ แ‹จแˆšแˆตแ‰ฐแŠซแŠจแˆˆแ‹ แˆตแˆซ แˆตแˆ‹แˆˆแ‰ฅแŠ แ‰ถแˆŽ แ‰ขแˆ†แŠ•แˆแŠ แŒฅแˆฉ แŠแ‹
๐Ÿค– What this model heard
แˆ˜แ‰ธ แŠแ‹ แ‹จแˆšแ‰ฐแŠซแŠจแˆˆแ‹ แˆตแ‰ฃแˆˆ แ‰ฐแˆŽ แˆˆแˆ†แŠ แˆ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
2
Correct
5
Wrong
2
Missed
0
Extra
22%
Words right
Out of 9 spoken words, this model got 2 right (22%). Errors: 5 words wrong; 2 missed.

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