Voice Chunk Size #287

New Issue

helloitsme · 2023-06-29T08:24:37Z

helloitsme commented

2023-06-29 08:24:37 +00:00

Voice Chunks: a slider to determine how many pieces to process your voice dataset when computing conditional latents. The lower the number, the bigger the pieces and the more VRAM is needed. The smaller the pieces, the less VRAM is needed, but the more likely you will slice mid-phoneme.

This is unclear. Would '1' require the most or least amount of VRAM?

`Voice Chunks: a slider to determine how many pieces to process your voice dataset when computing conditional latents. The lower the number, the bigger the pieces and the more VRAM is needed. The smaller the pieces, the less VRAM is needed, but the more likely you will slice mid-phoneme.` This is unclear. Would '1' require the most or least amount of VRAM?

psammites commented

2023-06-29 14:00:57 +00:00

No, the opposite.