SreyanG-NVIDIA commited on
Commit
529704c
·
verified ·
1 Parent(s): 2c92866

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -4
README.md CHANGED
@@ -72,15 +72,14 @@ Extensive evaluations confirm AF3’s effectiveness, setting new benchmarks on o
72
 
73
  **This model is for non-commercial research purposes only.**
74
 
 
 
 
75
  ## Model Architecture:
76
  Audio Flamingo 3 uses AF-Whisper unified audio encoder, MLP-based audio adaptor, Decoder-only LLM backbone (Qwen2.5-7B), and Streaming TTS module (AF3-Chat). Audio Flamingo 3 can take up to 10 minutes of audio inputs.
77
 
78
- <center><img src="static/af3_radial-1.png" width="400"></center>
79
-
80
- ## Results:
81
  <center><img src="static/af3_main_diagram-1.png" width="800"></center>
82
 
83
-
84
  ## License / Terms of Use
85
  The model is released under the [NVIDIA OneWay Noncommercial License](static/NVIDIA_OneWay_Noncommercial_License.docx). Portions of the dataset generation are also subject to the [Qwen Research License](https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE) and OpenAI’s [Terms of Use](https://openai.com/policies/terms-of-use).
86
 
 
72
 
73
  **This model is for non-commercial research purposes only.**
74
 
75
+ ## Results:
76
+ <center><img src="static/af3_radial-1.png" width="400"></center>
77
+
78
  ## Model Architecture:
79
  Audio Flamingo 3 uses AF-Whisper unified audio encoder, MLP-based audio adaptor, Decoder-only LLM backbone (Qwen2.5-7B), and Streaming TTS module (AF3-Chat). Audio Flamingo 3 can take up to 10 minutes of audio inputs.
80
 
 
 
 
81
  <center><img src="static/af3_main_diagram-1.png" width="800"></center>
82
 
 
83
  ## License / Terms of Use
84
  The model is released under the [NVIDIA OneWay Noncommercial License](static/NVIDIA_OneWay_Noncommercial_License.docx). Portions of the dataset generation are also subject to the [Qwen Research License](https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE) and OpenAI’s [Terms of Use](https://openai.com/policies/terms-of-use).
85