โ† All examples

ModelEthio-ASR Amharic (600M)1Ethio-ASR Multi (300M)6Ethio-ASR Multi (600M)2Ethio-ASR Multi (94M)7Meta MMS-1B9OmniASR-CTC (1B)3OmniASR-CTC (300M)5OmniASR-CTC (3B)3OmniASR-LLM (1B)3OmniASR-LLM (300M)5OmniASR-LLM (3B)3OpenAI Whisper-small9
Audio qualityClean Studio9Ambient Room Noise9Harsh Environment9Distant / Low-Volume Mic9Wideband Phone (VoLTE)9Randomized Phone Channel9Narrowband 2G + Packet Loss9

What did the model get wrong?

Meta MMS-1B Wideband Phone (VoLTE)   Example 8 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‰ แŒฃแˆ แŒฅแˆฉ แŠจแแ‰ฐแŠ›แ‹ แ‹จแแŒฅแАแ‰ต แˆ˜แŒ แŠ• แŠฅแˆตแŠจ แˆตแŠ•แ‰ต แАแ‹ แ‹จแˆšแ‹ฐแˆญแˆฐแ‹
๐Ÿค– What this model heard
แ‰  แ‰  แ‰ฝ แŒˆ แˆญ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
5
Wrong
4
Missed
0
Extra
0%
Words right
Out of 9 spoken words, this model got 0 right (0%). Errors: 5 words wrong; 4 missed.

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