SmolVLM: Redefining small and efficient multimodal models
Paper
•
2504.05299
•
Published
•
158
Whisper Distillation
community
AI & ML interests
Robust knowledge distillation of the Whisper model via large-scale pseudo-labelling.
Recent Activity
View all activity
distil-whisper's activity
Xenova
authored
a
paper
7 days ago
reach-vb
authored
a
paper
7 days ago
Move Transformers.js-compatible version to separate repo
#5 opened 21 days ago
by
Xenova
Xenova
updated
a
model
21 days ago
Move Transformers.js-compatible version to separate repo
#5 opened 21 days ago
by
Xenova
Xenova
updated
a
collection
21 days ago
Xenova
published
a
model
21 days ago
Update README.md
#4 opened 22 days ago
by
bofenghuang
Steveeeeeeen
published
3
models
22 days ago
Steveeeeeeen
updated
a
collection
22 days ago
Transformers.js - Enable external data format in Node.js
#13 opened about 1 month ago
by
Xenova
Adding ONNX file of this model
1
#11 opened 6 months ago
by
pavanteja007
Update to Transformers.js v3
#27 opened about 1 month ago
by
Xenova
Post
12920
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? 🔥
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?
Generate 10 seconds of speech in ~1 second for $0.
What will you build? 🔥
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?
- 11 replies
lmz
authored
a
paper
2 months ago