Thomas Pocreau

thomas-pocreau

pocman

AI & ML interests

None yet

Recent Activity

reacted to Xenova's post with 👍 about 2 months ago

Introducing Voxtral WebGPU: State-of-the-art audio transcription directly in your browser! 🤯 🗣️ Transcribe videos, meeting notes, songs and more 🔐 Runs on-device, meaning no data is sent to a server 🌎 Multilingual (8 languages) 🤗 Completely free (forever) & open source That's right, we're running Mistral's new Voxtral-Mini-3B model 100% locally in-browser on WebGPU, powered by Transformers.js and ONNX Runtime Web! 🔥 Try it out yourself! 👇 https://huggingface.co/spaces/webml-community/Voxtral-WebGPU

liked a Space about 2 months ago

mistralai/Voxtral-Realtime-WebGPU

liked a model about 2 months ago

onnx-community/Voxtral-Mini-4B-Realtime-2602-ONNX

View all activity

Organizations

None yet

liked a Space about 2 months ago

Voxtral Realtime WebGPU

💬

124

Real-time speech transcription, entirely in your browser.

liked a model about 2 months ago

onnx-community/Voxtral-Mini-4B-Realtime-2602-ONNX

Automatic Speech Recognition • Updated Mar 11 • 3.73k • 21

liked a dataset 2 months ago

imageomics/TreeOfLife-10M

Viewer • Updated Jan 15 • 6.13M • 2.39k • 47

liked 3 Spaces 2 months ago

Mosaïques Paysages

🌿

AI landscape composer with in-browser segmentation

SAM3 Tracker WebGPU

🎯

Segment images with click points and download cutouts

Qwen3.5 0.8B WebGPU

🦫

Generate AI descriptions of live video or video files

liked 2 models 2 months ago

onnx-community/Qwen3-0.6B-ONNX

Text Generation • Updated 20 days ago • 3k • 38

onnx-community/Qwen3.5-0.8B-ONNX

Image-Text-to-Text • Updated 17 days ago • 3.47k • 21

liked a Space 6 months ago

Qwen Image Edit Camera Control

🎬

2.21k

Fast 4 step inference with Qwen Image Edit 2509