v5.3.0: EuroBERT, VibeVoice ASR, TimesFM2.5, PP-DocLayoutV2, OlmoHybrid, ModernVBert, Higgs Audio V2

v5.3.0: EuroBERT, VibeVoice ASR, TimesFM2.5, PP-DocLayoutV2, OlmoHybrid, ModernVBert, Higgs Audio V2 huggingface / transformers Public Notifications You must be signed in to change notification settings Fork 34.7k Star 167k v5.3.0: EuroBERT, VibeVoice ASR, TimesFM2.5, PP-DocLayoutV2, OlmoHybrid, ModernVBert, Higgs Audio V2 LysandreJik released this 04 Mar 17:42 · 1921 commits to main since this release v5.3.0 aad13b8 New Model additions EuroBERT EuroBERT is a multilingual encoder model based on a refreshed transformer architecture, akin to Llama but with bidirectional attention. It supports a mixture of European and widely spoken languages, with sequences of up to 8192 tokens.

This SecurityIncident is relevant to the technology intelligence record because it involves GitHub, Microsoft, NVIDIA, Meta. The source article should remain the factual reference for follow-up coverage.

• huggingface / transformers Public Notifications You must be signed in to change notification settings Fork 34.7k Star 167k v5.3.0: EuroBERT, VibeVoice ASR, TimesFM2.5, PP-DocLayoutV2, OlmoHybrid, ModernVBert, Higgs Audio V2 LysandreJik released this 04 Mar 17:42 · 1921 commits to main since this release v5.3.0 aad13b8 New Model additions EuroBERT EuroBERT is a multilingual encoder model based on a refreshed transformer architecture, akin to Llama but with bidirectional attention.
• It supports a mixture of European and widely spoken languages, with sequences of up to 8192 tokens.
• Links: Documentation | Paper | Blog Post Add eurobert ( #39455 ) by @ArthurZucker in #39455 VibeVoice ASR VibeVoice ASR is an automatic speech recognition model from Microsoft that combines acoustic and semantic audio tokenizers with a causal language model for robust speech-to-text transcription.
• The model uses VibeVoice's acoustic and semantic tokenizers that process audio at 24kHz, paired with a Qwen2-based language decoder for generating transcriptions.
• It can process up to 60 minutes of continuous audio input, supports customized hotwords, performs joint ASR/diarization/timestamping, and handles over 50 languages with code-switching support.
• Links: Documentation | Paper Add VibeVoice ASR ( #43625 ) by @ebezzam in #43625 TimesFM2.5 TimesFM 2.5 is a pretrained time-series foundation model that uses a decoder-only attention architecture with input patching for forecasting.