โ† All examples

ModelEthio-ASR Amharic (600M)6Ethio-ASR Multi (300M)13Ethio-ASR Multi (600M)4Ethio-ASR Multi (94M)7Meta MMS-1B12OmniASR-CTC (1B)0OmniASR-CTC (300M)6OmniASR-CTC (3B)2OmniASR-LLM (1B)1OmniASR-LLM (300M)1OmniASR-LLM (3B)1OpenAI Whisper-small10
Audio qualityClean Studio0Ambient Room Noise0Harsh Environment0Distant / Low-Volume Mic0Wideband Phone (VoLTE)0Randomized Phone Channel2Narrowband 2G + Packet Loss12

What did the model get wrong?

OmniASR-CTC (3B) Randomized Phone Channel   Example 18 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Randomized Phone Channel
Phone-call audio with random extra distortions layered on top.
โœ… What was actually said
แ‰แŒฅแˆฌ แ‹œแˆฎ แ‹˜แŒ แŠ แŠ แˆแˆตแ‰ต แŠ แŠ•แ‹ต แŠ แŠ•แ‹ต แˆตแˆแŠ•แ‰ต แŠ แˆแˆตแ‰ต แŠ แŠ•แ‹ต แŠ แˆซแ‰ต แŠ แŠ•แ‹ต แŠแ‹
๐Ÿค– What this model heard
แ‰แŒฅแˆช แ‹œแˆฎ แ‹˜แŒ แ‹ญแŠ แŠ แˆแˆตแ‰ต แŠ แŠ•แ‹ต แŠ แŠ•แ‹ต แˆตแˆแŠ•แ‰ต แŠ แˆแˆตแ‰ต แŠ แŠ•แ‹ต แŠ แˆซแ‰ต แŠ แŠ•แ‹ต แŠแ‹
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
10
Correct
2
Wrong
0
Missed
0
Extra
83%
Words right
Out of 12 spoken words, this model got 10 right (83%). Errors: 2 words wrong.

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