โ† All examples

ModelEthio-ASR Amharic (600M)5Ethio-ASR Multi (300M)8Ethio-ASR Multi (600M)5Ethio-ASR Multi (94M)3Meta MMS-1B12OmniASR-CTC (1B)0OmniASR-CTC (300M)1OmniASR-CTC (3B)0OmniASR-LLM (1B)1OmniASR-LLM (300M)1OmniASR-LLM (3B)0OpenAI Whisper-small12
Audio qualityClean Studio12Ambient Room Noise11Harsh Environment12Distant / Low-Volume Mic12Wideband Phone (VoLTE)12Randomized Phone Channel10Narrowband 2G + Packet Loss12

What did the model get wrong?

OpenAI Whisper-small Wideband Phone (VoLTE)   Example 18 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‰แŒฅแˆฌ แ‹œแˆฎ แ‹˜แŒ แŠ แŠ แˆแˆตแ‰ต แŠ แŠ•แ‹ต แŠ แŠ•แ‹ต แˆตแˆแŠ•แ‰ต แŠ แˆแˆตแ‰ต แŠ แŠ•แ‹ต แŠ แˆซแ‰ต แŠ แŠ•แ‹ต แŠแ‹
๐Ÿค– What this model heard
แ‹œแˆฎzแŠ แŠ•แ‹ต
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
1
Wrong
11
Missed
0
Extra
0%
Words right
Out of 12 spoken words, this model got 0 right (0%). Errors: 1 word wrong; 11 missed.

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