Measured, not claimed
What changed, and by how much
Both models read the same held-out recordings through the same script with the same settings. The only difference between them is an 8.7 MB adapter trained for 52 minutes on one laptop GPU.
Both models read the same held-out recordings through the same script with the same settings. The only difference between them is an 8.7 MB adapter trained for 52 minutes on one laptop GPU.
Measured, not claimed
Both models read the same held-out recordings through the same script with the same settings. The only difference between them is an 8.7 MB adapter trained for 52 minutes on one laptop GPU.