โ† All examples

ModelEthio-ASR Amharic (600M)3Ethio-ASR Multi (300M)12Ethio-ASR Multi (600M)5Ethio-ASR Multi (94M)6Meta MMS-1B10OmniASR-CTC (1B)4OmniASR-CTC (300M)4OmniASR-CTC (3B)3OmniASR-LLM (1B)4OmniASR-LLM (300M)4OmniASR-LLM (3B)5OpenAI Whisper-small10
Audio qualityClean Studio6Ambient Room Noise5Harsh Environment4Distant / Low-Volume Mic5Wideband Phone (VoLTE)5Randomized Phone Channel5Narrowband 2G + Packet Loss10

What did the model get wrong?

Ethio-ASR Multi (600M) Randomized Phone Channel   Example 12 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
แŠ แˆแŠ• แ‹ซแˆˆแˆแ‰ต แŠ แ‹ณแˆ› แŠแ‹ แ‹ˆแ‹ฐ แŒ…แ‰กแ‰ฒ แˆˆแˆตแˆซ แˆแˆ„แ‹ต แˆตแˆˆแˆ†แŠ แŠแ‹
๐Ÿค– What this model heard
amh แŠ แˆแŠ• แ‹ซแˆˆแ‹ แ‰ณแ‹ณแˆ› แŠแ‹ แ‹ˆแ‹ฐ แŒ…แ‰กแ‰ฒ แˆตแˆซ แ‹ตแˆ„แ‹ต แˆตแˆˆแˆ†แŠ แŠแ‹
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
6
Correct
4
Wrong
0
Missed
1
Extra
60%
Words right
Out of 10 spoken words, this model got 6 right (60%). Errors: 4 words wrong; 1 extra.

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