โ All examples
What did the model get wrong?
OpenAI Whisper-small
Narrowband 2G + Packet Loss
Example 20 of 20
ยท speaker: Male
๐ง Listen โ Narrowband 2G + Packet Loss
Heavy background noise plus phone-call compression โ worst-case stress test.
โ
What was actually said
แแฅแฉ แแฎ แแ แ แแแต แแฎ แ แแตแต แตแตแตแต แฐแฃแต แตแแแต แแ แ แแฎ แแ
๐ค What this model heard
Out of 12 spoken words, this model got 0 right (0%). Errors: 12 missed.
Try switching Audio quality โ see the same model degrade as the audio gets noisier.