Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
๐ค
Open to Collab
Edison Manrique
EdiManrique
5
Follow
webbrain-a06's profile picture
webbrain-one-8907's profile picture
2 followers
ยท
11 following
ChocceEdison
edison-manrique
edison-manrique
AI & ML interests
None yet
Recent Activity
reacted
to
n4ze3m
's
post
with โ
1 day ago
I made a small English text-to-speech model called tiny-voca. It has 4.5M parameters, two voices, and it runs in your browser. Try it here, nothing is sent to a server: https://tiny-voca.n4ze3m.com Some facts: - 4,537,291 parameters, 18 MB. This is the whole model, the waveform part is included. - Two voices, one female and one male. 24 kHz. - About 70x faster than real time on 4 CPU threads. - Runs with PyTorch, ONNX, and in the browser. - Trained from scratch in 7.7 hours on one RTX 4090. What I think is different: - Everything is open. Code, weights, the training recipe and the dataset. - Custom phonemizer. - No neural vocoder. The sound is made by a small source-filter synth, which is why it is fast. What is not good yet: - English only, and only these two voices. No voice cloning. - Foreign names and odd spellings are often read wrong. - It can sound a bit synthetic. - The training audio is synthetic too. I made it with Qwen3-TTS, so the model can't sound better than that. Links: - Demo: https://tiny-voca.n4ze3m.com - Code: https://github.com/n4ze3m/tiny-voca - Weights: https://huggingface.co/n4ze3m/tiny-voca - Dataset: https://huggingface.co/datasets/n4ze3m/tiny-voca - Phonemizer: https://github.com/n4ze3m/dizione
liked
a model
1 day ago
n4ze3m/tiny-voca
liked
a Space
almost 2 years ago
black-forest-labs/FLUX.1-dev
View all activity
Organizations
None yet
models
0
None public yet
datasets
0
None public yet