โ† All examples

ModelEthio-ASR Amharic (600M)2Ethio-ASR Multi (300M)9Ethio-ASR Multi (600M)7Ethio-ASR Multi (94M)6Meta MMS-1B13OmniASR-CTC (1B)1OmniASR-CTC (300M)5OmniASR-CTC (3B)1OmniASR-LLM (1B)4OmniASR-LLM (300M)1OmniASR-LLM (3B)0OpenAI Whisper-small23
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 Wideband Phone (VoLTE)   Example 13 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Wideband Phone (VoLTE)
Compressed, narrow-band audio like a regular phone call.
โœ… What was actually said
แ‹ซแŠ›แ‹ แˆตแˆแŠญ แˆŒแˆ‹ แˆ˜แˆณแˆชแ‹ซ แˆ‹แ‹ญ แŠแ‹ แ‹ซแˆˆแ‹ แŠจแ‹šแˆ…แŠ›แ‹ แ‰แŒฅแˆญ แˆ‹แ‹ญ แˆ†แŠ˜ แˆ˜แŒจแˆจแˆต แŠ แˆแ‰ฝแˆแˆ
๐Ÿค– What this model heard
แ‹ซ แˆญ แŒˆแˆ˜ แ‹ แ‹ˆ แˆแˆต
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.