kcz358 commited on
Commit
4b365ec
·
verified ·
1 Parent(s): 7a9baa5

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -8
app.py CHANGED
@@ -84,18 +84,16 @@ with gr.Blocks() as demo:
84
  gr.Markdown("## 🎙️ Aero-1-Audio")
85
  gr.Markdown(
86
  """
87
- Aero-1-Audio is a compact audio model. With only 1.5B parameters and 50k hours training data, it can perform a variety of tasks, including:
88
- ASR, basic Audio Understanding, Audio Instruction Following, and scene analysis
89
 
90
- [🤗 Model Checkpoints](https://huggingface.co/lmms-lab/Aero-1-Audio-1.5B) | [📚 Blog](https://www.lmms-lab.com/posts/aero_audio/) | [📖 Evaluation Results](https://github.com/EvolvingLMMs-Lab/lmms-eval/pull/658) | [📚 Cookbook](https://www.lmms-lab.com/posts/lmms-lab-docs/aero_audio/)
91
 
92
- We provide several examples such as:
93
- - nvidia conference and a show from elon musk for long ASR
94
- - Simple Audio Instruction Following
95
- - Audio Understanding for weather and music
96
 
97
- The model might not be able to follow your instruction in multiple cases and might be wrong in many times
 
98
 
 
99
  """
100
  )
101
 
 
84
  gr.Markdown("## 🎙️ Aero-1-Audio")
85
  gr.Markdown(
86
  """
87
+ Aero-1-Audio is a lightweight audio-language model with only 1.5 billion parameters, trained on 50,000 hours of high-quality audio data. Despite its compact size, it supports a wide range of tasks, such as Automatic Speech Recognition (ASR), Basic Audio Understanding, Audio Instruction Following, and Scene Audio Analysis.
 
88
 
89
+ Notably, Aero-1-Audio excels at lossless ASR on ultra-long audio—up to 16 minutes—without the need for audio segmentation.
90
 
91
+ [📚 Blog](https://www.lmms-lab.com/posts/aero_audio/) | [🤗 Model Checkpoints](https://huggingface.co/lmms-lab/Aero-1-Audio-1.5B) | [📖 Evaluation Results](https://github.com/EvolvingLMMs-Lab/lmms-eval/pull/658) | [📚 Cookbook](https://www.lmms-lab.com/posts/lmms-lab-docs/aero_audio/)
 
 
 
92
 
93
+ To explore its capabilities, you can upload your own audio or record your voice directly.
94
+ Or simply start by trying the example demo below.
95
 
96
+ ⚠️ Disclaimer: Aero-1-Audio is still under active development. Occasional inaccuracies may occur. We appreciate your understanding and welcome any feedback to help us make it better.
97
  """
98
  )
99