# ONNX format

A model for detecting whether images contain Not Safe For Work (NSFW) content, supporting web deployment

Hiera is an efficient vision Transformer model designed for image classification tasks, featuring a small parameter count and high computational performance.

This is the ONNX format conversion of the MoritzLaurer/roberta-base-zeroshot-v2.0-c model, suitable for zero-shot classification tasks.

Object detection model based on YOLOv9 (GELAN-C) architecture, optimized ONNX version for Transformers.js

A depth estimation model based on Transformers.js, adapted for ONNX weights version, used to predict depth information from images.

Small ONNX-format depth estimation model adapted for Transformers.js framework, suitable for web-based depth map prediction

Chinese CLIP model based on Vision Transformer architecture, supporting cross-modal understanding and generation between images and text.

OWL-ViT is a zero-shot object detection model based on Vision Transformer, capable of detecting objects of new categories without fine-tuning.

A natural language inference (NLI) model based on the DeBERTa architecture, suitable for zero-shot classification tasks, converted to ONNX format for compatibility with Transformers.js

A small natural language inference model based on DeBERTa-v3, suitable for zero-shot classification tasks

Audio classification model based on wav2vec2 architecture, suitable for keyword detection tasks

ONNX weight version of OpenAI Whisper-tiny.en model, designed for Transformers.js, used for English speech transcription.