Corentin Jemine's picture

Corentin Jemine

CorentinJ

·

AI & ML interests

None yet

Recent Activity

updated a model about 1 month ago

CorentinJ/SV2TTS

replied to Xenova's post about 1 month ago

We did it. Kokoro TTS (v1.0) can now run 100% locally in your browser w/ WebGPU acceleration. Real-time text-to-speech without a server. ⚡️ Generate 10 seconds of speech in ~1 second for $0. What will you build? 🔥 https://huggingface.co/spaces/webml-community/kokoro-webgpu The most difficult part was getting the model running in the first place, but the next steps are simple: ✂️ Implement sentence splitting, allowing for streamed responses 🌍 Multilingual support (only phonemization left) Who wants to help?

published a model 4 months ago

CorentinJ/SV2TTS

View all activity

Organizations

None yet

updated a model about 1 month ago

CorentinJ/SV2TTS

Text-to-Speech • Updated Dec 15, 2025 • 1

replied to Xenova's post about 1 month ago

I've built a library for streaming pytorch models, and I decided to take Kokoro TTS for building a demo. In this demo I show how on CPU, 90% of the inference time is spent on kokoro's decoder and I make it streamable without sentence splitting. Here is the demo: https://torchstream.koyeb.app/streaming_kokoro_tts

And here is the project: https://github.com/CorentinJ/TorchStream

published a model 4 months ago

CorentinJ/SV2TTS

Text-to-Speech • Updated Dec 15, 2025 • 1