okestro-ai-lab
/

FastSLM-ASR

Audio-Text-to-Text

feature-extraction

text-generation

Model card Files Files and versions

speechisalluneed commited on Jan 27

Commit

29648f4

·

verified ·

1 Parent(s): 96bfefa

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -136,8 +136,8 @@ model-index:
 * 🔊 **HFQ-Former**: Hierarchically compresses high-frame-rate audio features while preserving the audio's local and global contextual information.
 * ⚡ **3-Stage Training**: Utilizes a cost-effective and fast training strategy.
 * 🧠 **LLM Adaptation**: Effectively adapts pre-trained Large Language Models (LLMs) to the audio modality.
-* ASR-specialized architecture** tailored for speech recognition tasks
-* Bilingual support (Korean & English)** in a single model
 ## 📖 Model Architecture

 * 🔊 **HFQ-Former**: Hierarchically compresses high-frame-rate audio features while preserving the audio's local and global contextual information.
 * ⚡ **3-Stage Training**: Utilizes a cost-effective and fast training strategy.
 * 🧠 **LLM Adaptation**: Effectively adapts pre-trained Large Language Models (LLMs) to the audio modality.
+* **ASR-specialized architecture** tailored for speech recognition tasks
+* **Bilingual support (Korean & English)** in a single model
 ## 📖 Model Architecture