Audio-Text-to-Text
Transformers
Safetensors
English
musicflamingo
text2text-generation
audio
speech
sound
music
reasoning
audio understanding
ASR
audio captioning
long-context
audio-language-model
long-audio
timestamp-grounding
instruction-tuned
Instructions to use nvidia/audio-flamingo-next-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/audio-flamingo-next-hf with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("nvidia/audio-flamingo-next-hf") model = AutoModelForSeq2SeqLM.from_pretrained("nvidia/audio-flamingo-next-hf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
audio.cpp now supports audio-flamingo-3 and audio-flamingo-next. C++/GGML. No Python. Q8 and Q4_K GGUFs provided.
👍 1
#4 opened about 1 month ago
by
audio-cpp
KeyError: 'audioflamingonext'
1
#3 opened 7 months ago
by
lby01
Poor word-level audio analysis performance
#2 opened 7 months ago
by
empeza
FP8 version
#1 opened 7 months ago
by
pbz134