โ† All examples

ModelEthio-ASR Amharic (600M)0Ethio-ASR Multi (300M)6Ethio-ASR Multi (600M)5Ethio-ASR Multi (94M)6Meta MMS-1B13OmniASR-CTC (1B)2OmniASR-CTC (300M)5OmniASR-CTC (3B)3OmniASR-LLM (1B)4OmniASR-LLM (300M)2OmniASR-LLM (3B)2OpenAI Whisper-small13
Audio qualityClean Studio4Ambient Room Noise5Harsh Environment5Distant / Low-Volume Mic4Wideband Phone (VoLTE)5Randomized Phone Channel3Narrowband 2G + Packet Loss13

What did the model get wrong?

OmniASR-CTC (300M) Harsh Environment   Example 13 of 20  ยท  speaker: Female

๐ŸŽง Listen โ€” Harsh Environment
Very heavy background noise โ€” much harder than typical audio.
โœ… What was actually said
แ‹ซแŠ›แ‹ แˆตแˆแŠญ แˆŒแˆ‹ แˆ˜แˆณแˆชแ‹ซ แˆ‹แ‹ญ แАแ‹ 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‹ซแŠ›แ‹ แˆตแ‹ตแŠญ แˆŒแˆ‹ แˆ˜แˆณแˆชแ‹ซ แˆ‹แ‹ญแŠ• แ‹ซแˆˆแ‹ แŠจแ‹šแˆ…แŠ›แ‹ แ‰แŒฅแˆญ แˆ‹แ‹ญ แˆ†แŠ˜ แˆ˜แŒจแˆจแˆณแˆแ‰ฝแˆ‰แˆ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
8
Correct
3
Wrong
2
Missed
0
Extra
62%
Words right
Out of 13 spoken words, this model got 8 right (62%). Errors: 3 words wrong; 2 missed.

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