47 2 6

Srinivas Billa PRO

srinivasbilla

nivibilla

AI & ML interests

None yet

Recent Activity

updated a Space 2 days ago

srinivasbilla/vc_chat

published a Space 2 days ago

srinivasbilla/vc_chat

updated a Space 3 days ago

srinivasbilla/llasa-8b-tts

View all activity

Organizations

None yet

srinivasbilla's activity

updated a Space 2 days ago

Vc Chat

📚

Transcribe and Synthesize Audio in Realtime

published a Space 2 days ago

Vc Chat

📚

Transcribe and Synthesize Audio in Realtime

updated a Space 3 days ago

Llasa 8b Tts

🔥

Zero Shot voice cloning with llasa 3b (Unofficial Demo)

commented on The SOTA Text-to-speech and Zero Shot Voice cloning model that no one knows about... 5 days ago

Yes! Thanks for letting me know

commented on The SOTA Text-to-speech and Zero Shot Voice cloning model that no one knows about... 8 days ago

around 10gb, and around 300 chars is the sweet spot. you can chunk text and do it though

New activity in srinivasbilla/optimus_prime_voicelines_hf 8 days ago

Librarian Bot: Add language metadata for dataset

#1 opened 9 days ago by

librarian-bot

liked a model 9 days ago

arcee-ai/Virtuoso-Medium-v2

Text Generation • Updated 9 days ago • 663 • 36

New activity in srinivasbilla/llasa-3b-tts 10 days ago

Can we run this locally via docker?

#4 opened 12 days ago by

pylotlight

New activity in srinivasbilla/llasa-3b-tts 11 days ago

Emotions

#3 opened 12 days ago by

jujutechnology

Fixes 500 error for some users

#2 opened 13 days ago by

Tonic

commented on The SOTA Text-to-speech and Zero Shot Voice cloning model that no one knows about... 15 days ago

I had a look at both, it seems doable. Ill try follow the repeng example. But its a bit confusing how they generate the dataset