Reverse Dependencies of transformers

The following projects have a declared dependency on transformers:

• vllm-npu — A high-throughput and memory-efficient inference and serving engine for LLMs
• vllm-xft — A high-throughput and memory-efficient inference and serving engine for LLMs
• VLM-Packages — no summary
• vlm-tools — Tools to work with the VLM-1 API.
• vlmvqa-python — VLmVQA tool
• vltk — The Vision-Language Toolkit (VLTK)
• vma-nlu — VMA-NLU is a library to implement NLU component in virtual medical assistant.
• VMedNLP — Medical NLP Toolkit
• vnhtr — Encoder-Decoder base for Vietnamese handwriting recognition
• vocab-coverage — 语言模型中文识字率分析
• vocably — Vocably is a Natural Language Framework written in Python for Language based Tasks.
• vocex — Voice Frame-Level and Utterance-Level Attribute Extraction
• vocoder-dictation — Dictation for programmers
• vocos — Fourier-based neural vocoder for high-quality audio synthesis
• void-terminal — LLM based APIs
• voltron-robotics — Voltron: Language-Driven Representation Learning for Robotics.
• VorlageLLM — Uses an LLM to determine which were plausible readings in the Vorlage of a translation of a text.
• vox-box — Vox box
• vptq — VPTQ (Vector Post-Training Quantization) is a novel Post-Training Quantization method.
• vqa-package — Visual Question Answering (VQA) package
• vqa-python — mVQA tool
• VTON — This is a test for my python package upload to pypi
• vtorch — NLP research library, built on PyTorch.
• vuldetectbench — VulDetectBench
• w5xde — Distributed machine learning
• wa-analyzer — Code for the Master of Applied Data Science course Data Analysis and Visualization
• waffle-hub — Waffle hub
• walledeval — An open-source toolkit to test LLMs against jailbreaks and unprecedented harms.
• wav-autoencoder — WavAutoencoder: A Self-Supervised Framework for Learning Audio Representations
• wd-llm-caption — A Python base cli tool for caption images with WD series, Joy-caption-pre-alpha, meta Llama 3.2 Vision Instruct, Qwen2 VL Instruct, Mini-CPM V2.6 and Florence-2 models.
• weak-annotators — Weak annotators for information extraction (NER)
• weather-chatbot-phi3 — An LLM Chatbot integrated with Open Weather API for Real-Time Weather Information.
• weather-retriever — Natural Language Weather Retriever
• webllama — Llama-powered agents for automatic web browsing
• websocietysimulator — Web Social Simulator for WWW'25 AgentSociety Challenge
• webull-options — no summary
• webwright — Webwright: The Ghost in Your Shell 👻💻
• wellcomeml — Utilities for managing nlp models and for processing text-related data at Wellcome Data Labs
• wepipe — no summary
• westac-parlaclarin-pipeline — Pipeline that transforms Parla-Clarin XML files
• wft — Run Whisper fine-tuning with ease.
• whatlies — Tools to help uncover `whatlies` in word embeddings.
• whisp — Whisper package
• whisper.ai — Robust Speech Recognition via Large-Scale Weak Supervision
• whisper-mic — Whisper for your microphone
• whisper-openai — Robust Speech Recognition via Large-Scale Weak Supervision
• whisper-realtime-transcriber — Let whisper models transcribe in realtime.
• whisper-run — Whisper with speaker diarization
• whisper-s2t — An Optimized Speech-to-Text Pipeline for the Whisper Model.
• whisper-speaker-id — Whisper Speaker Identification: A Python library for multiligual speaker identification and speaker embedding generation.
• whisper-timestamped — Multi-lingual Automatic Speech Recognition (ASR) based on Whisper models, with accurate word timestamps, access to language detection confidence, several options for Voice Activity Detection (VAD), and more.
• whisper-voice-commands — Execute scripts with Whisper for your microphone
• WhisperConformer — A library for Whisper Conformer model
• whisperer-ml — Go from raw audio to a text-audio dataset with OpenAI's Whisper
• whisperx — Time-Accurate Automatic Speech Recognition using Whisper.
• whisperx-numpy2-compatibility — A compatibility fix to allow whisperx to work with other packages that require numpy>2. Should no longer be required once pull requests on the main package are accepted.
• whisply — Transcribe, translate, annotate and subtitle audio and video files with OpenAI's Whisper ... fast!
• whitespace-correction — Correct missing or spurious whitespaces in text.
• whittle — Two-stage neural architecture search for large language models
• wide-analysis — A package for analyzing deletion discussions of Wiki platforms.
• wiki-passage-retriever — A small tool for retrieving relevant passages to a question from Wikipedia
• wildguard — WildGuard safety classification inference
• wildlife-tools — Tools for using wildlife re-identification datasets.
• wildtime — WILDS distribution shift benchmark
• windows-booknlp — no summary
• wirtual-plugins-turn-detection — End of utterance detection for LiveKit Agents
• word-injection — Fine-tuning Sentence Transformers with Word Injection technique
• word-piece-tokenizer — A Lightweight Word Piece Tokenizer
• wordsprobability — Method to get a words probability with fixes from How to Compute the Probability of a Word.
• wordtm — Topic Modeling Package
• wordwise — Keyword extraction using transformer-based language models
• wppkg — This package involves some functions I often use in my work.
• ws-benchmark — a weak supervision learning benchmark
• wsi-tissue-tiler — It makes small patches / tiles of large whole slide images available in svs format.
• wtpsplit — Universal Robust, Efficient and Adaptable Sentence Segmentation
• wvmos — This package is written for MOS score prediction based on fine-tuned wav2vec2.0 model
• Wyzard — Run various transformers models from one packages.
• x-tagger — A Natural Language Processing toolkit for token classification in its simplest form.
• x2vlm-gml — Package for X2-VLM, a vision-language model from ByteDance
• xai-explainer — A package for explaining deep learning models
• xaitk-jatic — Integration package to support interfacing, implementation and example needs for the JATIC.
• xares — eXtensive Audio Representation and Evaluation Suite
• xcodec2 — A library for XCodec2 model.
• xfinder — An Robust and Pinpoint Answer Extractor for LLM Evaluation
• xfuser — A Scalable Inference Engine for Diffusion Transformers (DiTs) on Multiple Computing Devices
• xgrammar — Efficient, Flexible and Portable Structured Generation
• xinfer — Framework agnostic computer vision inference. Run 1000+ models by changing only one line of code. Supports models from transformers, timm, ultralytics, vllm, ollama and your custom model.
• xinference — Model Serving Made Easy
• xl-bert — This lets you find sentence embedding using word embedding from XLNet and Bert
• xlagent — A lightweight framework for building LLM-based agents
• xlens — Add your description here
• xliff-ai-translator — AI-driven solution for efficient XLIFF/XLF file translation , bridging the gap between languages for localized content.
• xllm — Simple & Cutting Edge LLM Finetuning
• xlm-roberta-base-fine-tuning-text-classifier-lux — A library that leverages pre-trained XLM-RoBERTa models for multilingual text classification (French, German, English, and Luxembourgish) with easy-to-use fine-tuning capabilities.
• xLSTM — A novel LSTM variant with promising performance compared to Transformers or State Space Models.
• xmen — An extensible toolkit for Cross-lingual (x) Medical Entity Normalization.
• xretrieval — Retrieve and Evaluate with X(any) models
• xt-models — Models and model utilities for common ML tasks
• xt-nlp — Utilities for training and working with nlp models in pytorch
• xtal2txt — Package to encode and decode crystal structures into text representations