57 1 7

Darío Muñoz Prudant PRO

prudant

https://medium.com/@prudant

puppetm4st3r

AI & ML interests

Tech enthusiast, avid AI learner, and perpetual seeker of new knowledge.

Recent Activity

commented on an article 26 days ago

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

new activity 29 days ago

M-Chimiste/Llama-3-8B-prime-graph-exp-1_merged:3.1 llama version

new activity about 1 month ago

tiesenx14/Llama-3.1-8B-IT-GraphRAG-finetuned:help =)

View all activity

Organizations

prudant's activity

commented on SmolVLM Grows Smaller – Introducing the 250M & 500M Models! 26 days ago

❤️

New activity in M-Chimiste/Llama-3-8B-prime-graph-exp-1_merged 29 days ago

3.1 llama version

#1 opened 29 days ago by

prudant

New activity in tiesenx14/Llama-3.1-8B-IT-GraphRAG-finetuned about 1 month ago

help =)

#1 opened about 1 month ago by

prudant

New activity in NLDoc/lilt-xlm-roberta-base-finetuned-DocLayNet-large_paragraphs_ml512-v1-cp5000 about 2 months ago

how to use this model?

#1 opened about 2 months ago by

prudant

New activity in Mit1208/Florence-2-large-DocLayNet about 2 months ago

Finetune code

#1 opened about 2 months ago by

prudant

reacted to reach-vb's post with 👀 3 months ago

Post

1711

Smol TTS models are here! OuteTTS-0.1-350M - Zero shot voice cloning, built on LLaMa architecture, CC-BY license! 🔥

> Pure language modeling approach to TTS
> Zero-shot voice cloning
> LLaMa architecture w/ Audio tokens (WavTokenizer)
> BONUS: Works on-device w/ llama.cpp ⚡

Three-step approach to TTS:

> Audio tokenization using WavTokenizer (75 tok per second)
> CTC forced alignment for word-to-audio token mapping
> Structured prompt creation w/ transcription, duration, audio tokens

The model is extremely impressive for 350M parameters! Kudos to the
OuteAI team on such a brilliant feat - I'd love to see this be applied on larger data and smarter backbones like SmolLM 🤗

Check out the models here: OuteAI/outetts-6728aa71a53a076e4ba4817c