Instructions to use Qwen/Qwen2-Audio-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen2-Audio-7B-Instruct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct") model = AutoModelForSeq2SeqLM.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct") - Notebooks
- Google Colab
- Kaggle
Fixed bugs with latest transformers.
#27
by RezaAMehr - opened
Processor takes audio as a parameter (not audios)
Input items are all set to CUDA
used max_new_tokens to consider the output token limit, not input+output.