1 5 53

Haolei

holyhigh666

AI & ML interests

None yet

Recent Activity

liked a Space 5 days ago

Mobvoi/Offical-Spark-TTS

liked a Space 9 days ago

fastrtc/whisper-realtime

liked a model 10 days ago

microsoft/Phi-4-multimodal-instruct

View all activity

Organizations

None yet

holyhigh666's activity

liked a Space 5 days ago

185

Spark TTS

🌖

A text-to-speech model powered by SparkAudio and Mobvoi.

liked a Space 9 days ago

Whisper Realtime Transcription

👂

Transcribe audio in realtime with Whisper

liked a model 10 days ago

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • Updated 5 days ago • 637k • 1.16k

upvoted an article 20 days ago

Article

FastRTC: The Real-Time Communication Library for Python

21 days ago

• 145

liked a Space 21 days ago

SmolVLM2 XSPFGenerator (VLC prototype)

🎞

Generate video highlights and playlist

liked a model 21 days ago

ahmed-masry/chartgemma

Image-Text-to-Text • Updated Jul 27, 2024 • 1.54k • 41

updated a Space 24 days ago

Paddle OCR

📈

An unofficial demo of Paddle OCR.

reacted to lysandre's post with ❤️ 24 days ago

Post

5670

SmolVLM-2 and SigLIP-2 are now part of transformers in dedicated releases!

They're added on top of the v4.49.0 release, and can be installed from the following tags: v4.49.0-SmolVLM-2 and v4.49.0-SigLIP-2.

This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).

Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.

Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.