Popular repositories Loading

1. Qwen2-vl-audio Qwen2-vl-audio Public

   Qwen2-VL with a shared frozen Whisper encoder for speech and music audio-visual QA

   Python 2

2. qwen2-vl-nutrition-table qwen2-vl-nutrition-table Public

   Fine-tuning Qwen2-VL-7B to detect nutrition tables in product images — 0.82 mean IoU, served at 17.8 req/s with vLLM

   Python

3. transformers transformers Public

   Forked from huggingface/transformers

   🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

   Python

4. qwen-vl-utils qwen-vl-utils Public

   Fork of qwen-vl-utils extended with audio loading utilities (fetch_audio, process_audio_info) for ASR pipelines

   Python