โ† All examples

ModelEthio-ASR Amharic (600M)4Ethio-ASR Multi (300M)8Ethio-ASR Multi (600M)5Ethio-ASR Multi (94M)7Meta MMS-1B12OmniASR-CTC (1B)7OmniASR-CTC (300M)8OmniASR-CTC (3B)3OmniASR-LLM (1B)7OmniASR-LLM (300M)0OmniASR-LLM (3B)0OpenAI Whisper-small12
Audio qualityClean Studio7Ambient Room Noise1Harsh Environment2Distant / Low-Volume Mic7Wideband Phone (VoLTE)2Randomized Phone Channel2Narrowband 2G + Packet Loss6

What did the model get wrong?

OmniASR-CTC (1B) Clean Studio   Example 9 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Clean Studio
Clear, studio-quality recording. Best-case audio.
โœ… What was actually said
แ‰แŒฅแˆฉ แ‹œแˆฎ แ‹˜แŒ แŠ แŠ แŠ•แ‹ต แˆแˆˆแ‰ต แŠ แˆแˆตแ‰ต แˆตแ‹ตแˆตแ‰ต แˆฐแ‰ฃแ‰ต แˆตแˆแŠ•แ‰ต แ‹˜แŒ แŠ แ‹œแˆฎ แАแ‹
๐Ÿค– What this model heard
แ‰แŒฅแˆฉ แ‹œแˆฎแ‹˜แŒ  แŠ แŠ•แ‹ต แˆแˆˆแ‰ต แŠ แˆแˆตแ‰ต แˆตแ‹ตแˆต แ‰ฃแ‰ต แˆตแˆแŠ•แ‰ตแˆแ‹˜ แ‹œ แАแ‹
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
5
Correct
5
Wrong
2
Missed
0
Extra
42%
Words right
Out of 12 spoken words, this model got 5 right (42%). Errors: 5 words wrong; 2 missed.

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