63 2 8

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

new activity about 6 hours ago

gaunernst/gemma-3-27b-it-qat-autoawq:How you convert from guff to AWQ

updated a dataset 22 days ago

dolfsai/toxic_es

new activity 27 days ago

michaelfeil/mxbai-rerank-large-v2-seq:quants?

View all activity

Organizations

prudant's activity

New activity in gaunernst/gemma-3-27b-it-qat-autoawq about 6 hours ago

How you convert from guff to AWQ

#3 opened about 7 hours ago by

prudant

updated a dataset 22 days ago

dolfsai/toxic_es

Viewer • Updated 22 days ago • 50.9k • 178 • 1

New activity in michaelfeil/mxbai-rerank-large-v2-seq 27 days ago

quants?

#3 opened 30 days ago by

prudant

New activity in nvidia/Llama-3_3-Nemotron-Super-49B-v1 29 days ago

Create FP4 version

#6 opened about 2 months ago by

rombodawg

New activity in dolfsai/toxic_es about 1 month ago

[bot] Conversion to Parquet

#1 opened about 1 month ago by

parquet-converter

published a dataset about 1 month ago

dolfsai/toxic_es

Viewer • Updated 22 days ago • 50.9k • 178 • 1

updated a Space about 1 month ago

README

😻

published a Space about 1 month ago

README

😻

updated a dataset about 1 month ago

clenp/toxic_es

Updated about 1 month ago • 30

published a dataset about 1 month ago

clenp/toxic_es

Updated about 1 month ago • 30

upvoted a collection about 1 month ago

InternVL3

Collection

34 items • Updated 24 days ago • 67

New activity in ds4sd/SmolDocling-256M-preview about 2 months ago

Layout detection mode?

#25 opened about 2 months ago by

prudant

liked a model 2 months ago

Qwen/QwQ-32B-AWQ

Text Generation • Updated Mar 11 • 82k • 124

commented on SmolVLM Grows Smaller – Introducing the 250M & 500M Models! 4 months ago

❤️

reacted to reach-vb's post with 👀 6 months ago

Post

1885

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