How to use mispeech/r1-aqa with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("mispeech/r1-aqa") model = AutoModelForSeq2SeqLM.from_pretrained("mispeech/r1-aqa")
94b86bf
1
2
3
4
5
6
7
{ "audio_bos_token": "<|audio_bos|>", "audio_eos_token": "<|audio_eos|>", "audio_token": "<|AUDIO|>", "processor_class": "Qwen2AudioProcessor" }
