โ† All examples

ModelEthio-ASR Amharic (600M)1Ethio-ASR Multi (300M)2Ethio-ASR Multi (600M)2Ethio-ASR Multi (94M)4Meta MMS-1B9OmniASR-CTC (1B)3OmniASR-CTC (300M)1OmniASR-CTC (3B)1OmniASR-LLM (1B)1OmniASR-LLM (300M)1OmniASR-LLM (3B)1OpenAI Whisper-small43
Audio qualityClean Studio43Ambient Room Noise18Harsh Environment9Distant / Low-Volume Mic26Wideband Phone (VoLTE)9Randomized Phone Channel22Narrowband 2G + Packet Loss12

What did the model get wrong?

OpenAI Whisper-small Clean Studio   Example 8 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Clean Studio
Clear, studio-quality recording. Best-case audio.
โœ… What was actually said
แ‰ แŒฃแˆ แŒฅแˆฉ แŠจแแ‰ฐแŠ›แ‹ แ‹จแแŒฅแŠแ‰ต แˆ˜แŒ แŠ• แŠฅแˆตแŠจ แˆตแŠ•แ‰ต แŠแ‹ แ‹จแˆšแ‹ฐแˆญแˆฐแ‹
๐Ÿค– What this model heard
bet i m do you know can you have a coffee time to do that you can t get to net me if it s not met and it s just a net met and it s cousin to know me there so
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
9
Wrong
0
Missed
34
Extra
0%
Words right
Out of 9 spoken words, this model got 0 right (0%). Errors: 9 words wrong; 34 extra.

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