全站搜索

AI 模型 84997

• spkrec-ecapa-voxceleb↗

  speechbrain

  This repository provides all the necessary tools to perform speaker verification with a pretrained ECAPA-TDNN model using SpeechBrain. The system can be used to extract speaker embeddings as well. It is trained on Voxceleb 1+ Voxceleb2 training data. For a better experience, we encourage you to learn more about SpeechBrain. The model performance on Voxceleb1-test set(Cleaned) is: This system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss. Speaker Verification is performed using cosine distance between speaker embeddings.

• Sugoi-32B-Ultra-GGUF↗

  sugoitoolkit

• Qwen3.5-4B-NVFP4↗

  surogate

• Qwen3.8-2B-heretic↗

  Tanjiro20

• Qwen3-VL-8B-Instruct-Eagle3↗

  taobao-mnn

• Kimiko-v2-13B-GGUF↗

  TheBloke

• efficientnet_es.ra_in1k↗

  timm

• maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k↗

  timm

• regnety_064.ra3_in1k↗

  timm

  The `timm` RegNet implementation includes a number of enhancements not present in other implementations, including: * stochastic depth * gradient checkpointing * layer-wise LR decay * configurable output stride (dilation) * configurable activation and norm layers * option for a pre-activation bottleneck block used in RegNetV variant * only known RegNetZ model definitions with pretrained weights For the comparison summary below, the ra_in1k, ra3_in1k, ch_in1k, sw_*, and lion_* tagged weights are trained in `timm`.

• STAR1-R1-Distill-14B↗

  UCSC-VLAA