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")
Question 1: How to make qwen2-audio outptu asr result with timestamp ?
Question 2: During training, which stage used the timestamped annotated ASR transcript?
· Sign up or log in to comment
