dolfsai/toxic_es
Viewer
•
Updated
•
50.9k
•
31
•
1
Darío Muñoz Prudant PRO
prudant
AI & ML interests
Tech enthusiast, avid AI learner, and perpetual seeker of new knowledge.
Recent Activity
updated
a dataset
about 12 hours ago
dolfsai/toxic_es
new activity
5 days ago
michaelfeil/mxbai-rerank-large-v2-seq:quants?
new activity
7 days ago
nvidia/Llama-3_3-Nemotron-Super-49B-v1:Create FP4 version
Organizations
prudant's activity
updated
a
dataset
about 12 hours ago
Create FP4 version
1
2
#6 opened about 1 month ago
by
rombodawg
[bot] Conversion to Parquet
#1 opened 8 days ago
by
parquet-converter
published
a
dataset
8 days ago
updated
a
Space
8 days ago
published
a
Space
8 days ago
updated
a
dataset
8 days ago
published
a
dataset
8 days ago
upvoted
a
collection
10 days ago
Layout detection mode?
2
4
#25 opened about 1 month ago
by
prudant
liked
a
model
about 2 months ago
commented on
SmolVLM Grows Smaller – Introducing the 250M & 500M Models!
3 months ago
❤️
reacted to
reach-vb's
post with 👀
5 months ago
Post
1842
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
> 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
How to use visual grounding with this model ?
2
#25 opened 7 months ago
by
r4hul77
Documentation?
1
1
#1 opened about 1 year ago
by
ThewindMom
A practical use case from your great job for the spanish language
1
4
#9 opened 10 months ago
by
prudant
upvoted
an
article
6 months ago
Article
¡Lanzamiento de la Comunidad Latinoamericana de NLP en Hugging Face! 🌟
By
•
•
7
published
an
article
6 months ago
Article
¡Lanzamiento de la Comunidad Latinoamericana de NLP en Hugging Face! 🌟
By
•
•
7
updated
a
Space
7 months ago