โ All examples
What did the model get wrong?
OpenAI Whisper-small
Clean Studio
Example 10 of 20
ยท speaker: Male
๐ง Listen โ Clean Studio
Clear, studio-quality recording. Best-case audio.
โ
What was actually said
แตแ แฅแ
แแน แแญแแญ แแจแ แจแต แแ แจแแแแ
๐ค What this model heard
แแฎxแแฎ
Out of 7 spoken words, this model got 0 right (0%). Errors: 1 word wrong; 6 missed.
Try switching Audio quality โ see the same model degrade as the audio gets noisier.