Audio-Text-to-Text
Transformers
Safetensors
English
audioflamingo3
text2text-generation
audio
reasoning
audio understanding
ASR
Instructions to use nvidia/audio-flamingo-3-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/audio-flamingo-3-hf with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("nvidia/audio-flamingo-3-hf") model = AutoModelForSeq2SeqLM.from_pretrained("nvidia/audio-flamingo-3-hf") - Notebooks
- Google Colab
- Kaggle
transformers package version
#2
by arjunpaw - opened
the latest transformers package (4.57.1) doesn't seem to have the class AudioFlamingo3ForConditionalGeneration as stated in the example code
Hi, I have the same error. Have you solved it?
Should work now! It just got merged!
Also it isn't in a release (yet), but you can pull from source: https://github.com/huggingface/transformers
SreyanG-NVIDIA changed discussion status to closed