サイト内検索

AI モデル 84759

• XORTRON.CriminalComputing.LARGE.2026.3↗

  darkc0de

• google.gemma-4-E2B-it-qat-q4_0-unquantized-GGUF↗

  DevQuasar

• blaser-2.0-ref↗

  facebook

• fasttext-sc-vectors↗

  facebook

• mms-tts-ppk↗

  facebook

• mms-tts-wal-script_ethiopic↗

  facebook

• FastVideo-FastH3-Comfy↗

  FastVideo

  Original model repository: https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2

• eus-latn-10mb-after-ppt-Dp-100mb-packed-bfdiso-ckpt500_seed10↗

  francesca9805

• rus-cyrl-100mb-after-ppt-Dp-10mb-packed-bfdiso-ckpt500_seed3407↗

  francesca9805

• Fun-ASR-Nano-2512-GGUF↗

  FunAudioLLM

  Standalone audio.cpp GGUF builds of FunAudioLLM/Fun-ASR-Nano-2512-hf. Each file embeds the model configuration, processor configuration, tokenizer, chat template, and the audio.cpp model package specification. The source checkpoint is pinned to revision `854d88f94205cd17d2afdb24332130d86fbe654a`. The source `model.safetensors` SHA256 is `335ca3e74917f1156690400e2c344350112950165789cf78ce3d0a367affd821`. Fun-ASR-Nano currently provides offline multilingual ASR. It does not expose streaming or timestamp output. On CUDA, audio.cpp keeps the Q8_0 encoder and adaptor weights native and loads decoder weights as BF16 by default for stable logits. An explicit `fun_asr_nano.decoder_weight_type` session option overrides that default.