Update README.md

README.md

@@ -11,24 +11,19 @@ tags:
 <img src="https://cdn-uploads.huggingface.co/production/uploads/6618e0424dbef6bd3c72f89a/d7Rzpm0cgCToXjtE7_U2u.png" alt="Example" style="width:200px;"/>
 
 # OmniAudio-2.6B
-OmniAudio is the world's fastest and most efficient audio-language model for on-device deployment - a 2.6B-parameter multimodal model that processes both text and audio inputs. It integrates three components: **Gemma-2-2b**, **Whisper turbo**, and a custom projector module, enabling secure, responsive audio-text processing directly on edge devices.
+OmniAudio is the world's fastest and most efficient audio-language model for on-device deployment - a 2.6B-parameter multimodal model that processes both text and audio inputs. It integrates three components: Gemma-2-2b, Whisper turbo, and a custom projector module, enabling secure, responsive audio-text processing directly on edge devices.
 Unlike traditional approaches that chain ASR and LLM models together, OmniAudio-2.6B unifies both capabilities in a single efficient architecture for minimal latency and resource overhead.
-
-On a 2024 Mac Mini M4 Pro using Q4_K_M quantized GGUF model, **Qwen2-Audio-7B** processes 1.69 tokens/second while OmniAudio-2.6B achieves 4.97 tokens/second, demonstrating nearly **3x faster performance** on consumer hardware.
-
+On a 2024 Mac Mini M4 Pro, **Qwen2-Audio-7B-Instruct** running on 🤗 Transformers achieves an average decoding speed of 6.38 tokens/second, while **Omni-Audio-2.6B** through Nexa SDK reaches 35.23 tokens/second in FP16 GGUF version and 66 tokens/second in Q4_K_M quantized GGUF version - delivering **5.5x to 10.3x faster performance** on consumer hardware.
 ## Quick Links
 1. Interactive Demo in our [HuggingFace Space]().
 2. [Quickstart for local setup]()
 3. Learn more in our [Blogs]()
-4. **Feedback**: Send questions or suggestions about the model in our [Discord](https://discord.gg/nexa-ai)
-
 ## Use Cases
 * **Voice QA without Internet**: Process offline voice queries like "I am at camping, how do I start a fire without fire starter?" OmniAudio provides practical guidance even without network connectivity.
 * **Voice-in Conversation**: Have conversations about personal experiences. When you say "I am having a rough day at work," OmniAudio engages in supportive talk and active listening.
 * **Creative Content Generation**: Transform voice prompts into creative pieces. Ask "Write a haiku about autumn leaves" and receive poetic responses inspired by your voice input.
 * **Recording Summary**: Simply ask "Can you summarize this meeting note?" to convert lengthy recordings into concise, actionable summaries.
 * **Voice Tone Modification**: Transform casual voice memos into professional communications. When you request "Can you make this voice memo more professional?" OmniAudio adjusts the tone while preserving the core message.
-
 ## Run OmniAudio-2.6B on Your Device
 **Step 1: Install Nexa-SDK (local on-device inference framework)**
 [Install Nexa-SDK](https://github.com/NexaAI/nexa-sdk?tab=readme-ov-file#install-option-1-executable-installer)
@@ -38,14 +33,11 @@ On a 2024 Mac Mini M4 Pro using Q4_K_M quantized GGUF model, **Qwen2-Audio-7B**
 nexa run omniaudio -st
 ```
 💻 OmniAudio-2.6B q4_K_M version requires 1.30GB RAM and 1.60GB storage space.
-
 ## Training
 We developed OmniAudio through a three-stage training pipeline:
-
-* **Pretraining:** The initial stage focuses on core audio-text alignment using MLS English 10k transcription dataset. We introduced a special <|transcribe|> token to enable the model to distinguish between transcription and completion tasks, ensuring consistent performance across use cases.
-* **Supervised Fine-tuning (SFT):** We enhance the model's conversation capabilities using synthetic datasets derived from MLS English 10k transcription. This stage leverages a proprietary model to generate contextually appropriate responses, creating rich audio-text pairs for effective dialogue understanding.
-* **Direct Preference Optimization (DPO):** The final stage refines model quality using GPT-4o API as a reference. The process identifies and corrects inaccurate responses while maintaining semantic alignment. We additionally leverage Gemma2's text responses as a gold standard to ensure consistent quality across both audio and text inputs.
-
+**Pretraining:** The initial stage focuses on core audio-text alignment using MLS English 10k transcription dataset. We introduced a special <|transcribe|> token to enable the model to distinguish between transcription and completion tasks, ensuring consistent performance across use cases.
+**Supervised Fine-tuning (SFT):** We enhance the model's conversation capabilities using synthetic datasets derived from MLS English 10k transcription. This stage leverages a proprietary model to generate contextually appropriate responses, creating rich audio-text pairs for effective dialogue understanding.
+**Direct Preference Optimization (DPO):** The final stage refines model quality using GPT-4o API as a reference. The process identifies and corrects inaccurate responses while maintaining semantic alignment. We additionally leverage Gemma2's text responses as a gold standard to ensure consistent quality across both audio and text inputs.
 ## What's Next for OmniAudio?
 OmniAudio is in active development and we are working to advance its capabilities:
 * Building direct audio generation for two-way voice communication