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
Marat
maratos
3
2
5
Follow
dipankarsarkar's profile picture
1 follower
ยท
1 following
AI & ML interests
None yet
Recent Activity
updated
a Space
4 days ago
VoxRT/linnet-tts
updated
a model
4 days ago
VoxRT/linnet-en-35m
replied
to
their
post
8 days ago
LinnetTTS: a 41 M-parameter English text-to-speech model with voice prompts that streams from the first 80 ms and runs in real time on one phone CPU core. Code Apache-2.0; weights under the Linnet Weights License (free to use in your own products, commercial included). Same machine, same three texts, each model through its own Python package. Speed only, quality not measured: - Linnet 41 M: RTF 10.6 % on one core (3.4 % on four), first audio 87 ms, 187 MB RSS, voice prompts, streams every 80 ms - pocket-tts 100 M: 23.8 % on two cores, 968 MB, voice prompts, streams every 80 ms - Kokoro-82M: 51.7 %, 1.2 GB, whole utterance per call, 8 languages - Piper medium 16 M: 5.8 %, 503 MB, no voice prompts, per-sentence chunks On phones: iPhone 13 Pro Max 5.5 ms per 80 ms step, iPhone 11 7 ms, Snapdragon 662 14 ms on four cores. ๐ง Hear the same sentence from all four, side by side: the "Compare" tab of the demo Space https://huggingface.co/spaces/VoxRT/linnet-tts (type your own text for Linnet there too) ๐ฆ Weights and model card: https://huggingface.co/VoxRT/linnet-en-35m ๐ฆ Code, Rust runtime, bindings for Linux C, Python (pip install linnet-tts), Android and iOS, and the benchmark script: https://github.com/VoxRT/LinnetTTS ๐ Method: https://github.com/VoxRT/LinnetTTS/blob/main/docs/benchmarks.md ๐ Write-up with the trade-offs and the samples: https://huggingface.co/blog/VoxRT/small-cpu-text-to-speech-models-compared-piper-kok ๐ Collection of small CPU TTS models and their demos: https://huggingface.co/collections/VoxRT/on-device-tts-small-models-that-run-on-a-cpu-6aec390f2f84a4407d227cf4 English only for now; no text normalisation, so write numbers as words. If it is useful to you, a like on the model or the Space helps other people find it. Questions welcome.
View all activity
Organizations
maratos
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a Space
10 days ago
Running
Agents
5
LinnetTTS
๐ฆ
5
On-device TTS, 41M params, streaming, real time on CPU
liked
a model
10 days ago
VoxRT/linnet-en-35m
Text-to-Speech
โข
Updated
4 days ago
โข
285
โข
7
liked
3 models
4 months ago
VoxRT/silero-vad-vxrt
Voice Activity Detection
โข
Updated
Sep 15
โข
2
VoxRT/wake-word-hey-assistant-vxrt
Audio Classification
โข
Updated
Sep 15
โข
2
VoxRT/streaming-medium-pc-vxrt
Automatic Speech Recognition
โข
Updated
Sep 15
โข
1