dodin

dodin
ยท

AI & ML interests

None yet

Recent Activity

liked a model 7 days ago
microsoft/Florence-2-large
liked a model 5 months ago
Qwen/Qwen2-VL-7B-Instruct
liked a model 6 months ago
aiola/whisper-medusa-v1
View all activity

Organizations

None yet

dodin's activity

replied to thomwolf's post 9 months ago
reacted to thomwolf's post with โค๏ธ๐Ÿ”ฅ 9 months ago
view post
Post
4889
Is is time for the open-source AI robots revolution ๐Ÿš€?

With @haixuantao and @Leyo weโ€™ve been playing with a low-cost DJI robot controlled by three local open-source AI models (Whisper, Idefics2, Parler-TTS - all Apache2) and orchestrated by Dora-cs.

Links to find all the hardware/software we used in the demo:
- robot control framework โ€“ dora-rs: https://github.com/dora-rs/dora
- speech-to-text model โ€“ whisper: openai/whisper-base
- vision-text model โ€“ Idefics2: HuggingFaceM4/idefics2-8b-AWQ
- text-to-speech model โ€“ ParlerTTS mini: parler-tts/parler_tts_mini_v0.1
- robot: https://dji.com/robomaster-s1
- code gist: https://gist.github.com/haixuanTao/860e1740245dc2c8dd85b496150a9320
- Larger codebase: dora-rs/dora-idefics2
- laptop/pc: any with a recent GPU card (our has a RTX 4090)

Enjoy!
ยท