전체 검색

AI 모델 84759

• LoopedLM-P1-dense-ouro-336b↗

  IFM

• internlm2-step-prover↗

  internlm

• deberta-v2-base-japanese↗

  izumi-lab

• habibi-tts-doda-darija↗

  Jip7e

• Qwen3.8-27B-DASHQ-Q2-GGUF↗

  jkim96

• gemma-4-E4B-it-uncensored-heretic-UD-GGUF↗

  JMingo

• gpt-oss-20b-keep30-MXFP4-GGUF↗

  Joakimpalm-Zen

• kb-whisper-large↗

  KBLab

  The National Library of Sweden releases a new suite of Whisper models trained on over 50,000 hours of Swedish speech. In evaluations across FLEURS, CommonVoice and NST, our best performing model reduces the Word Error Rate (WER) by an average of 47% compared to OpenAI's `whisper-large-v3`. The performance of smaller Whisper model sizes on Swedish speech has also substantially improved, with `kb-whisper-small` outperforming `openai/whisper-large-v3` (a model six times its size). Table: **Word Error Rate (WER)** comparison between KBLab's Whisper models and the corresponding OpenAI versions. We provide checkpoints in different formats: `Hugging Face`, `whisper.cpp` (GGML), `onnx`, and `ctranslate2` (used in `faster-whisper` and `WhisperX`).

• Qwen3.8-9B-mlx-4Bit↗

  keXjos

  The Model keXjos/Qwen3.8-9B-mlx-4Bit was converted to MLX format from empero-ai/Qwen3.8-9B using mlx-lm version **0.31.2**.

• ms-eff-gcvit-deepfake-b0-kodf↗

  KoreaPeter

  Multi-Scale Efficient Global Context Vision Transformer (MS-EffGCViT) is a hybrid CNN-ViT architecture for **deepfake detection**. It fuses CNN-driven spatial inductive bias with hierarchical global-context attention to catch both *local* artifacts (textures, blending seams) and *global* artifacts (lighting, structural inconsistency). A single architecture ships in two sizes and three domain-tuned checkpoints, working on both **static images** and **video** at the **frame level**. While traditional Vision Transformers (ViTs) utilize a Linear Projection for patch embedding, our proposed model adopts a CNN-based Patch Embedding module incorporating MBConvBlocks.