10
Llasa 1B Multi Speakers Genshin Zh En Ja Ko
🚀
Llasa-1B-Multilingual finetuned using simon3000/genshin-voic
Wang
Winston33
·
AI & ML interests
None yet
Recent Activity
liked
a Space
27 days ago
HKUST-Audio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
commented on
an
article
27 days ago
From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages
Organizations
None yet
Winston33's activity
liked
a
Space
27 days ago
upvoted
an
article
27 days ago
Article
From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages
By
and 1 other
•
•
26
commented on
From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages
27 days ago
Hi，very appreciate your blog on Llasa. And I want to finetune the model. I noticed that fine-tuning a 1B model requires 24GB of VRAM. Could you please provide an estimate of the VRAM requirements for fine-tuning 3B and 8B models? Additionally, how much finetuning data in terms of hours of WAV files would be required for these models?
liked
a
model
about 1 month ago
