โ† All examples

ModelEthio-ASR Amharic (600M)1Ethio-ASR Multi (300M)9Ethio-ASR Multi (600M)5Ethio-ASR Multi (94M)6Meta MMS-1B10OmniASR-CTC (1B)4OmniASR-CTC (300M)2OmniASR-CTC (3B)2OmniASR-LLM (1B)4OmniASR-LLM (300M)6OmniASR-LLM (3B)1OpenAI Whisper-small10
Audio qualityClean Studio10Ambient Room Noise10Harsh Environment10Distant / Low-Volume Mic10Wideband Phone (VoLTE)10Randomized Phone Channel10Narrowband 2G + Packet Loss10

What did the model get wrong?

Meta MMS-1B Wideband Phone (VoLTE)   Example 12 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
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
แ‰ตแŠ  แˆแ‰ฝแˆˆ แˆ›แˆ‹แ‰  แ‹ญแˆ˜ แˆ แˆ
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
6
Wrong
4
Missed
0
Extra
0%
Words right
Out of 10 spoken words, this model got 0 right (0%). Errors: 6 words wrong; 4 missed.

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