Upload 3 files

README.md

@@ -1,14 +1,91 @@
 ---
-title: Audio Reasoning Explorer
-emoji: 👀
-colorFrom: blue
-colorTo: gray
+title: Audio Reasoning & Step-Audio-R1 Explorer
+emoji: 🎧
+colorFrom: purple
+colorTo: blue
 sdk: gradio
-sdk_version: 6.0.0
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
-license: mit
-short_description: Interactive Hugging Face Space for exploring audio reasoning
+license: cc-by-4.0
+short_description: Interactive guide to audio reasoning and Step-Audio-R1 model
+tags:
+  - audio
+  - reasoning
+  - multimodal
+  - step-audio-r1
+  - LALM
+  - chain-of-thought
+  - education
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🎧 Audio Reasoning & Step-Audio-R1 Explorer
+
+An interactive educational space exploring the groundbreaking concepts behind **audio reasoning** and the **Step-Audio-R1** model.
+
+## 🎯 What is Audio Reasoning?
+
+Audio reasoning is an AI model's ability to perform **deliberate, multi-step thinking processes** over audio inputs. This goes far beyond simple speech recognition (ASR) or audio classification.
+
+**Step-Audio-R1** is the first model to successfully unlock reasoning capabilities in the audio domain, solving the "inverted scaling anomaly" that plagued previous audio language models.
+
+## 🚀 Features of This Space
+
+| Tab | Content |
+|-----|---------|
+| 🏠 **Introduction** | Overview of audio reasoning and key achievements |
+| 🧠 **Reasoning Types** | Interactive explorer for 5 types of audio reasoning |
+| 🚫 **The Problem** | Understanding the inverted scaling anomaly |
+| 🔬 **MGRD Solution** | How Modality-Grounded Reasoning Distillation works |
+| 🏗️ **Architecture** | Step-Audio-R1 model architecture breakdown |
+| 📊 **Benchmarks** | Performance comparisons and results |
+| 🎮 **Interactive Demo** | Simulated audio reasoning examples |
+| 🚀 **Applications** | Real-world use cases |
+| 📚 **Resources** | Papers, code, and references |
+
+## 🔬 Key Innovation: MGRD
+
+**Modality-Grounded Reasoning Distillation (MGRD)** is the core innovation that makes Step-Audio-R1 work:
+
+```
+Text-based reasoning → Filter textual surrogates → Keep acoustic-grounded chains → Native Audio Think
+```
+
+This iterative process teaches the model to reason over **actual acoustic features** instead of text transcripts.
+
+## 📊 Performance
+
+Step-Audio-R1 achieves:
+- ✅ **Surpasses Gemini 2.5 Pro** on comprehensive audio benchmarks
+- ✅ **Comparable to Gemini 3 Pro** (state-of-the-art)
+- ✅ **First successful test-time compute scaling** for audio
+
+## 📚 Resources
+
+- 📄 [Step-Audio-R1 Paper](https://arxiv.org/abs/2511.15848)
+- 💻 [GitHub Repository](https://github.com/stepfun-ai/Step-Audio-R1)
+- 🤗 [HuggingFace Collection](https://huggingface.co/collections/stepfun-ai/step-audio-r1)
+- 🎯 [Official Demo](https://stepaudiollm.github.io/step-audio-r1/)
+
+## 👤 Author
+
+**Mehmet Tuğrul Kaya**
+- 🐙 GitHub: [@mtkaya](https://github.com/mtkaya)
+- 🤗 HuggingFace: [tugrulkaya](https://huggingface.co/tugrulkaya)
+
+## 📝 Citation
+
+```bibtex
+@article{stepaudioR1,
+  title={Step-Audio-R1 Technical Report},
+  author={Tian, Fei and others},
+  journal={arXiv preprint arXiv:2511.15848},
+  year={2025}
+}
+```
+
+---
+
+<p align="center">
+  <b>🎧 Sound Speaks, AI Listens and Thinks 🧠</b>
+</p>

app.py

@@ -0,0 +1,853 @@
+"""
+🎧 Audio Reasoning & Step-Audio-R1 Explorer
+Interactive Hugging Face Space for exploring audio reasoning concepts
+
+Author: Mehmet Tuğrul Kaya
+"""
+
+import gradio as gr
+
+# ============================================
+# CONTENT DATA
+# ============================================
+
+INTRO_CONTENT = """
+# 🎧 Audio Reasoning & Step-Audio-R1
+
+## Teaching AI to Think About Sound
+
+**Step-Audio-R1** is the first audio language model to successfully unlock reasoning capabilities in the audio domain. 
+This space explores the groundbreaking concepts behind audio reasoning and the innovative MGRD framework.
+
+### 🎯 Key Achievement
+> *"Can audio intelligence truly benefit from deliberate thinking?"* — **YES!**
+
+Step-Audio-R1 proves that reasoning is a **transferable capability across modalities** when properly grounded in acoustic features.
+
+---
+
+### 📊 Quick Stats
+
+| Metric | Value |
+|--------|-------|
+| **Model Size** | 32B parameters (Qwen2.5 LLM) |
+| **Audio Encoder** | Qwen2 (25 Hz, frozen) |
+| **Performance** | Surpasses Gemini 2.5 Pro |
+| **Innovation** | First successful audio reasoning model |
+
+---
+
+*Navigate through the tabs to explore different aspects of audio reasoning!*
+"""
+
+# Audio Reasoning Types Data
+REASONING_TYPES = {
+    "Factual Reasoning": {
+        "emoji": "📋",
+        "description": "Extracting concrete information from audio",
+        "example_question": "What date is mentioned in this conversation?",
+        "example_audio": "A business call discussing a meeting scheduled for March 15th",
+        "what_model_does": "Identifies specific facts, numbers, names, dates from speech content",
+        "challenge": "Requires accurate speech recognition + information extraction"
+    },
+    "Procedural Reasoning": {
+        "emoji": "📝",
+        "description": "Understanding step-by-step processes and sequences",
+        "example_question": "What is the third step in this instruction set?",
+        "example_audio": "A cooking tutorial explaining how to make pasta",
+        "what_model_does": "Tracks sequential information, understands ordering and dependencies",
+        "challenge": "Must maintain context across long audio segments"
+    },
+    "Normative Reasoning": {
+        "emoji": "⚖️",
+        "description": "Evaluating social, ethical, or behavioral norms",
+        "example_question": "Is the speaker behaving appropriately in this dialogue?",
+        "example_audio": "A customer service call with an upset customer",
+        "what_model_does": "Assesses tone, politeness, social appropriateness based on context",
+        "challenge": "Requires understanding of social norms + prosodic analysis"
+    },
+    "Contextual Reasoning": {
+        "emoji": "🌍",
+        "description": "Inferring environmental and situational context",
+        "example_question": "Where might this sound have been recorded?",
+        "example_audio": "Background noise with birds, wind, and distant traffic",
+        "what_model_does": "Analyzes ambient sounds to determine location/situation",
+        "challenge": "Must process non-speech audio elements"
+    },
+    "Causal Reasoning": {
+        "emoji": "🔗",
+        "description": "Establishing cause-effect relationships",
+        "example_question": "Why might this sound event have occurred?",
+        "example_audio": "A loud crash followed by glass breaking",
+        "what_model_does": "Infers causality from sound sequences and patterns",
+        "challenge": "Requires world knowledge + temporal understanding"
+    }
+}
+
+# The Problem Content
+PROBLEM_CONTENT = """
+## 🚫 The Inverted Scaling Anomaly
+
+### The Paradox
+Traditional audio language models showed a **strange behavior**: they performed **WORSE** when reasoning longer!
+
+This is the opposite of what happens in text models (like GPT-4, Claude) where more thinking = better answers.
+
+### Root Cause: Textual Surrogate Reasoning
+
+```
+🔊 Audio Input
+      ↓
+📝 Model converts to text (transcript)
+      ↓
+🧠 Reasons over TEXT, not SOUND
+      ↓
+❌ Acoustic features IGNORED
+      ↓
+💀 Performance degrades with longer reasoning
+```
+
+### Why Does This Happen?
+
+1. **Text-based initialization**: Models are fine-tuned from text LLMs
+2. **Inherited patterns**: They learn to reason like text models
+3. **Modality mismatch**: Audio is treated as "text with extra steps"
+4. **Lost information**: Tone, emotion, prosody, ambient sounds are ignored
+
+### Real Example
+
+**Audio**: Person says "Sure, I'll do it" in a *sarcastic, annoyed tone*
+
+| Approach | Interpretation |
+|----------|---------------|
+| **Textual Surrogate** ❌ | "Person agrees to do the task" |
+| **Acoustic-Grounded** ✅ | "Person is reluctant/annoyed, may not follow through" |
+
+The acoustic-grounded approach captures the TRUE meaning!
+"""
+
+# MGRD Content
+MGRD_CONTENT = """
+## 🔬 MGRD: Modality-Grounded Reasoning Distillation
+
+MGRD is the **key innovation** that makes Step-Audio-R1 work. It's an iterative training framework that teaches the model to reason over actual acoustic features instead of text surrogates.
+
+### The MGRD Pipeline
+
+```
+┌─────────────────────────────────────────────────┐
+│           MGRD ITERATIVE PROCESS                │
+├─────────────────────────────────────────────────┤
+│                                                 │
+│  START: Text-based reasoning (inherited)        │
+│              ↓                                  │
+│  ITERATION 1: Generate reasoning chains         │
+│              ↓                                  │
+│  FILTER: Remove textual surrogate chains        │
+│              ↓                                  │
+│  SELECT: Keep acoustically-grounded chains      │
+│              ↓                                  │
+│  RETRAIN: Update model with filtered data       │
+│              ↓                                  │
+│  REPEAT until "Native Audio Think" emerges      │
+│              ↓                                  │
+│  RESULT: Model reasons over acoustic features!  │
+│                                                 │
+└─────────────────────────────────────────────────┘
+```
+
+### Three Training Stages
+
+| Stage | Name | What Happens |
+|-------|------|--------------|
+| **1** | Cold-Start | SFT + RLVR to establish basic audio understanding |
+| **2** | Iterative Distillation | Filter and refine reasoning chains |
+| **3** | Native Audio Think | Model develops true acoustic reasoning |
+
+### What Makes a "Good" Reasoning Chain?
+
+**❌ Bad (Textual Surrogate):**
+> "The speaker says 'I'm fine' so they must be feeling okay."
+
+**✅ Good (Acoustically-Grounded):**
+> "The speaker's voice shows elevated pitch (+15%), faster tempo, and slight tremor, indicating stress despite saying 'I'm fine'. The background noise suggests a busy environment which may be contributing to their tension."
+
+The good chain references **actual acoustic features**!
+"""
+
+# Architecture Content
+ARCHITECTURE_CONTENT = """
+## 🏗️ Step-Audio-R1 Architecture
+
+Step-Audio-R1 builds on Step-Audio 2 with three main components:
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                 STEP-AUDIO-R1 ARCHITECTURE                  │
+├─────────────────────────────────────────────────────────────┤
+│                                                             │
+│  🎤 AUDIO INPUT (waveform)                                  │
+│         │                                                   │
+│         ▼                                                   │
+│  ┌─────────────────────────────────┐                       │
+│  │      AUDIO ENCODER              │                       │
+│  │   • Qwen2 Audio Encoder         │                       │
+│  │   • 25 Hz frame rate            │                       │
+│  │   • FROZEN during training      │                       │
+│  └─────────────────────────────────┘                       │
+│         │                                                   │
+│         ▼                                                   │
+│  ┌─────────────────────────────────┐                       │
+│  │      AUDIO ADAPTOR              │                       │
+│  │   • 2x downsampling             │                       │
+│  │   • 12.5 Hz output              │                       │
+│  │   • Bridge to LLM               │                       │
+│  └─────────────────────────────────┘                       │
+│         │                                                   │
+│         ▼                                                   │
+│  ┌─────────────────────────────────┐                       │
+│  │      LLM DECODER                │                       │
+│  │   • Qwen2.5 32B                 │                       │
+│  │   • Core reasoning engine       │                       │
+│  │   • Outputs: Think → Response   │                       │
+│  └───────��─────────────────────────┘                       │
+│         │                                                   │
+│         ▼                                                   │
+│  📝 TEXT OUTPUT                                             │
+│     <thinking>...</thinking>                                │
+│     <response>...</response>                                │
+│                                                             │
+└─────────────────────────────────────────────────────────────┘
+```
+
+### Component Details
+
+| Component | Model | Frame Rate | Status |
+|-----------|-------|------------|--------|
+| Audio Encoder | Qwen2 Audio | 25 Hz | Frozen |
+| Audio Adaptor | Custom MLP | 12.5 Hz (2x down) | Trainable |
+| LLM Decoder | Qwen2.5 32B | N/A | Trainable |
+
+### Output Format
+
+The model produces structured reasoning:
+
+```xml
+<thinking>
+1. Acoustic Analysis: [describes sound properties]
+2. Pattern Recognition: [identifies key features]  
+3. Inference: [draws conclusions from audio]
+</thinking>
+
+<response>
+[Final answer based on acoustic reasoning]
+</response>
+```
+"""
+
+# Benchmarks Data
+BENCHMARK_DATA = """
+## 📊 Benchmark Results
+
+Step-Audio-R1 was evaluated on comprehensive audio understanding benchmarks:
+
+### MMAU (Massive Multi-Task Audio Understanding)
+- **10,000** audio clips with human-annotated Q&A
+- **27** distinct skills tested
+- Covers: Speech, Environmental Sounds, Music
+
+### Performance Comparison
+
+| Model | MMAU Avg | vs Gemini 2.5 Pro |
+|-------|----------|-------------------|
+| **Step-Audio-R1** | **~78%** | **+12%** ✅ |
+| Gemini 3 Pro | ~77% | +11% |
+| Gemini 2.5 Pro | ~66% | baseline |
+| GPT-4o Audio | ~55% | -11% |
+| Qwen2.5-Omni | ~52% | -14% |
+
+### The Breakthrough: Test-Time Compute Scaling
+
+```
+BEFORE Step-Audio-R1:
+More thinking → ❌ Worse performance (inverted scaling)
+
+AFTER Step-Audio-R1:
+More thinking → ✅ Better performance (normal scaling)
+```
+
+**This is the first time test-time compute scaling works for audio!**
+
+### Domain Performance
+
+| Domain | Step-Audio-R1 | Previous SOTA |
+|--------|---------------|---------------|
+| Speech | 🟢 High | Medium |
+| Sound | 🟢 High | Medium |
+| Music | 🟢 High | Low |
+"""
+
+# Applications Content
+APPLICATIONS_CONTENT = """
+## 🚀 Practical Applications
+
+Audio reasoning enables many new AI capabilities:
+
+### 1. 🎙️ Advanced Voice Assistants
+- Understand complex multi-step instructions
+- Detect user emotion and adjust responses
+- Handle ambiguous requests intelligently
+
+### 2. 📞 Call Center Analytics
+- Analyze customer sentiment in real-time
+- Detect escalation patterns before they happen
+- Extract action items from conversations
+
+### 3. ♿ Accessibility Tools
+- Rich audio descriptions for hearing impaired
+- Environmental sound narration
+- Music content analysis and description
+
+### 4. 🔒 Security & Monitoring
+- Anomalous sound event detection
+- Contextual threat assessment
+- Multi-source audio analysis
+
+### 5. 🎓 Education & Learning
+- Pronunciation analysis for language learning
+- Music performance evaluation
+- Lecture comprehension and Q&A
+
+### Example: Meeting Analysis
+
+```
+📥 Input: [30-minute team meeting recording]
+
+🤔 Step-Audio-R1 Analysis:
+
+<thinking>
+1. Speaker identification: 4 distinct voices detected
+2. Topic tracking: Budget discussion (0-10min), 
+   Project timeline (10-20min), Action items (20-30min)
+3. Sentiment analysis: 
+   - Speaker A: Confident, leading discussion
+   - Speaker B: Concerned (elevated pitch during budget section)
+   - Speaker C: Disengaged (low energy, minimal contributions)
+   - Speaker D: Supportive, mediating tensions
+4. Key moments: Tension spike at 8:42 (disagreement on budget)
+</thinking>
+
+<response>
+Meeting Summary:
+- Main topics: Q3 budget allocation, Project Alpha timeline
+- Key decision: Budget approved with 10% reduction
+- Action items: 3 identified (assigned to Speakers A, B, D)
+- Team dynamics: Some tension around budget, resolved by end
+- Follow-up recommended: 1-on-1 with Speaker C (low engagement)
+</response>
+```
+"""
+
+# Resources Content
+RESOURCES_CONTENT = """
+## 📚 Resources & Links
+
+### 📄 Papers
+| Paper | Link |
+|-------|------|
+| Step-Audio-R1 Technical Report | [arXiv:2511.15848](https://arxiv.org/abs/2511.15848) |
+| MMAU Benchmark | [arXiv:2410.19168](https://arxiv.org/abs/2410.19168) |
+| Audio-Reasoner | [arXiv:2503.02318](https://arxiv.org/abs/2503.02318) |
+| SpeechR Benchmark | [arXiv:2508.02018](https://arxiv.org/abs/2508.02018) |
+
+### 💻 Code & Models
+| Resource | Link |
+|----------|------|
+| Step-Audio-R1 GitHub | [github.com/stepfun-ai/Step-Audio-R1](https://github.com/stepfun-ai/Step-Audio-R1) |
+| Step-Audio-R1 Demo | [stepaudiollm.github.io/step-audio-r1](https://stepaudiollm.github.io/step-audio-r1/) |
+| HuggingFace Collection | [huggingface.co/collections/stepfun-ai/step-audio-r1](https://huggingface.co/collections/stepfun-ai/step-audio-r1) |
+| AudioBench | [github.com/AudioLLMs/AudioBench](https://github.com/AudioLLMs/AudioBench) |
+
+### 📖 Key Concepts Glossary
+
+| Term | Full Name | Description |
+|------|-----------|-------------|
+| **LALM** | Large Audio Language Model | AI model that understands and reasons over audio |
+| **CoT** | Chain-of-Thought | Step-by-step reasoning approach |
+| **MGRD** | Modality-Grounded Reasoning Distillation | Training framework for acoustic reasoning |
+| **TSR** | Textual Surrogate Reasoning | Problem where model reasons over text instead of audio |
+| **RLVR** | Reinforcement Learning with Verified Rewards | Training with binary correctness rewards |
+| **SFT** | Supervised Fine-Tuning | Standard fine-tuning on labeled data |
+
+### 📝 Citation
+
+```bibtex
+@article{stepaudioR1,
+  title={Step-Audio-R1 Technical Report},
+  author={Tian, Fei and others},
+  journal={arXiv preprint arXiv:2511.15848},
+  year={2025}
+}
+```
+
+---
+
+### 👤 About This Space
+
+Created by **Mehmet Tuğrul Kaya**
+- 🐙 GitHub: [@mtkaya](https://github.com/mtkaya)
+- 🤗 HuggingFace: [tugrulkaya](https://huggingface.co/tugrulkaya)
+
+*This educational space explores the concepts behind Step-Audio-R1 and audio reasoning.*
+"""
+
+# ============================================
+# HELPER FUNCTIONS
+# ============================================
+
+def get_reasoning_type_info(reasoning_type):
+    """Get detailed information about a reasoning type"""
+    if reasoning_type not in REASONING_TYPES:
+        return "Please select a reasoning type"
+    
+    info = REASONING_TYPES[reasoning_type]
+    
+    output = f"""
+## {info['emoji']} {reasoning_type}
+
+### Description
+{info['description']}
+
+### Example Question
+> *"{info['example_question']}"*
+
+### Example Audio Scenario
+🎧 {info['example_audio']}
+
+### What the Model Does
+{info['what_model_does']}
+
+### Key Challenge
+⚠️ {info['challenge']}
+
+---
+
+### How Step-Audio-R1 Handles This
+
+Unlike traditional models that would convert this to text first, Step-Audio-R1:
+
+1. **Analyzes acoustic features** directly from the audio waveform
+2. **Generates reasoning chains** grounded in sound properties
+3. **Produces answers** that account for non-verbal information
+
+This is what makes it the first true **audio reasoning** model!
+"""
+    return output
+
+
+def create_comparison_chart():
+    """Create model comparison data"""
+    return """
+### 📊 Model Comparison on MMAU Benchmark
+
+| Rank | Model | Score | Type |
+|------|-------|-------|------|
+| 🥇 | **Step-Audio-R1** | ~78% | Open |
+| 🥈 | Gemini 3 Pro | ~77% | Proprietary |
+| 🥉 | Gemini 2.5 Pro | ~66% | Proprietary |
+| 4 | Audio Flamingo 3 | ~60% | Open |
+| 5 | GPT-4o Audio | ~55% | Proprietary |
+| 6 | Qwen2.5-Omni | ~52% | Open |
+
+**Key Insight**: Step-Audio-R1 is the first **open** model to match proprietary SOTA!
+"""
+
+
+def generate_demo_reasoning(scenario):
+    """Generate example reasoning for demo scenarios"""
+    scenarios = {
+        "Customer Service Call": """
+## 🎧 Demo: Customer Service Call Analysis
+
+**Scenario**: A customer calls about a billing issue
+
+### Simulated Audio Description
+- Customer voice: Female, middle-aged, American English
+- Tone: Initially frustrated, becomes calmer
+- Agent voice: Male, professional, empathetic tone
+- Background: Quiet call center environment
+- Duration: ~3 minutes
+
+### Step-Audio-R1 Reasoning (Simulated)
+
+```xml
+<thinking>
+1. SPEAKER ANALYSIS:
+   - Customer: F0 mean 220Hz (elevated), speech rate 4.2 syl/sec (fast)
+   - Initial segment shows tension markers: pitch variation +40%
+   - Gradual calming: pitch stabilizes by minute 2
+   
+2. AGENT ANALYSIS:
+   - Consistent calm prosody throughout
+   - Strategic pauses after customer complaints
+   - Mirroring technique detected (matching customer's pace)
+
+3. EMOTIONAL ARC:
+   - 0:00-0:45: Customer frustrated (anger markers)
+   - 0:45-1:30: Tension peak, interruption detected
+   - 1:30-2:30: De-escalation successful
+   - 2:30-3:00: Resolution, positive closing
+
+4. ACOUSTIC CONTEXT:
+   - Low background noise suggests professional environment
+   - No hold music interruptions
+   - Clear audio quality on both sides
+</thinking>
+
+<response>
+This customer service interaction shows successful de-escalation. 
+The customer initially displayed frustration (elevated pitch, fast 
+speech) but the agent's calm, empathetic approach led to resolution.
+Key success factor: Agent's strategic use of pauses and mirroring.
+Customer satisfaction likely: HIGH (based on closing tone).
+</response>
+```
+""",
+        "Meeting Recording": """
+## 🎧 Demo: Meeting Recording Analysis
+
+**Scenario**: Team standup meeting (15 minutes)
+
+### Simulated Audio Description
+- 4 speakers in conference room
+- Mixed engagement levels
+- Some background office noise
+- One speaker joins via video call
+
+### Step-Audio-R1 Reasoning (Simulated)
+
+```xml
+<thinking>
+1. SPEAKER IDENTIFICATION:
+   - Speaker A (Lead): Clear, confident, 65% of speaking time
+   - Speaker B (Remote): Slight compression artifacts, engaged
+   - Speaker C (Junior): Hesitant prosody, brief contributions
+   - Speaker D (Senior): Minimal input, possible disengagement
+
+2. TOPIC TRACKING:
+   - 0:00-5:00: Sprint review (Speaker A leading)
+   - 5:00-10:00: Blockers discussion (B raises concern)
+   - 10:00-15:00: Planning next steps
+
+3. ENGAGEMENT ANALYSIS:
+   - Speaker C shows uncertainty (rising intonation on statements)
+   - Speaker D energy levels low (F0 variance minimal)
+   - Remote Speaker B most engaged despite audio quality
+
+4. ACOUSTIC ENVIRONMENT:
+   - Room reverb suggests medium conference room
+   - HVAC noise consistent throughout
+   - Remote connection stable (no dropouts)
+
+5. KEY MOMENTS:
+   - 6:23: Tension spike (overlapping speech, raised voices)
+   - 12:45: Agreement reached (synchronized acknowledgments)
+</thinking>
+
+<response>
+Meeting Analysis Summary:
+- Duration: 15 minutes, 4 participants
+- Key discussion: Sprint blockers and resolution
+- Action items identified: 3 (assigned to Speakers A, B, C)
+- Team dynamics note: Speaker D showed low engagement - 
+  recommend follow-up. Speaker C may need support (uncertainty 
+  markers detected in their updates).
+- Overall meeting effectiveness: MODERATE
+</response>
+```
+""",
+        "Podcast Episode": """
+## 🎧 Demo: Podcast Episode Analysis
+
+**Scenario**: Tech podcast interview (45 minutes)
+
+### Simulated Audio Description
+- Host and guest conversation
+- Professional studio recording
+- Music intro/outro
+- Natural conversational flow
+
+### Step-Audio-R1 Reasoning (Simulated)
+
+```xml
+<thinking>
+1. AUDIO QUALITY ASSESSMENT:
+   - Studio-quality recording (low noise floor)
+   - Two distinct microphones detected
+   - Music segments: Intro (0:00-0:30), Outro (44:30-45:00)
+   - No significant audio issues
+
+2. SPEAKER DYNAMICS:
+   - Host: Experienced interviewer, good pacing
+   - Guest: Expert on topic, occasional filler words
+   - Turn-taking: Natural, minimal interruptions
+   - Rapport: Strong (laughter at 12:34, 23:45, 38:12)
+
+3. CONTENT STRUCTURE:
+   - Introduction: 0:30-3:00
+   - Main discussion: 3:00-40:00
+   - Audience Q&A: 40:00-44:30
+   - Closing: 44:30-45:00
+
+4. ENGAGEMENT INDICATORS:
+   - Energy peaks: 15:00 (exciting announcement)
+   - Deep technical discussion: 25:00-32:00
+   - Emotional moment: 35:00 (personal story shared)
+
+5. PROSODIC ANALYSIS:
+   - Guest becomes more animated on specific topics
+   - Host maintains consistent energy throughout
+   - Pace accelerates during exciting segments
+</thinking>
+
+<response>
+Podcast Episode Analysis:
+- Format: Interview style, 45 minutes
+- Quality: Professional studio recording
+- Key topics: [Inferred from discussion patterns]
+- Highlight moments: 15:00 (announcement), 35:00 (personal story)
+- Listener engagement prediction: HIGH
+- Recommended clips for promotion: 15:00-16:30, 35:00-36:45
+- Overall quality: EXCELLENT (clear audio, good rapport, 
+  well-structured conversation)
+</response>
+```
+""",
+        "Music Analysis": """
+## 🎧 Demo: Music Analysis
+
+**Scenario**: Unknown music track analysis
+
+### Simulated Audio Description
+- Instrumental track
+- ~4 minutes duration
+- Multiple instruments
+- Studio production
+
+### Step-Audio-R1 Reasoning (Simulated)
+
+```xml
+<thinking>
+1. ACOUSTIC ANALYSIS:
+   - Tempo: ~120 BPM (moderate, danceable)
+   - Key: A minor (melancholic but energetic)
+   - Time signature: 4/4
+   - Dynamic range: 12 dB (well-mastered)
+
+2. INSTRUMENTATION:
+   - Drums: Electronic, four-on-the-floor pattern
+   - Bass: Synthesizer, prominent low-end
+   - Lead: Analog-style synth, saw wave
+   - Pads: Ambient, reverb-heavy
+   - No vocals detected
+
+3. STRUCTURE:
+   - Intro: 0:00-0:30 (buildup)
+   - Verse 1: 0:30-1:30 (main groove)
+   - Build: 1:30-2:00 (tension)
+   - Drop: 2:00-2:30 (energy peak)
+   - Verse 2: 2:30-3:30 (variation)
+   - Outro: 3:30-4:00 (fadeout)
+
+4. PRODUCTION ANALYSIS:
+   - Sidechain compression detected on pads
+   - Stereo width: Wide (good separation)
+   - Reference similar to: Melodic techno genre
+   - Production quality: Professional
+
+5. EMOTIONAL CHARACTER:
+   - Overall mood: Driving but melancholic
+   - Energy arc: Building → Peak → Sustain → Release
+</thinking>
+
+<response>
+Music Analysis Summary:
+- Genre: Melodic Techno / Progressive House
+- Tempo: 120 BPM
+- Key: A minor
+- Duration: ~4 minutes
+- Mood: Energetic yet melancholic
+- Production: Professional quality, well-mastered
+- Use cases: DJ sets, workout playlists, focus music
+- Similar artists: [Based on production style]
+- Standout elements: Strong bass design, effective buildup
+</response>
+```
+"""
+    }
+    
+    return scenarios.get(scenario, "Please select a scenario")
+
+
+# ============================================
+# GRADIO INTERFACE
+# ============================================
+
+# Custom CSS
+custom_css = """
+.gradio-container {
+    max-width: 1200px !important;
+}
+.tab-nav button {
+    font-size: 16px !important;
+}
+.prose h1 {
+    color: #FF6B35 !important;
+}
+.prose h2 {
+    color: #4ECDC4 !important;
+    border-bottom: 2px solid #4ECDC4;
+    padding-bottom: 5px;
+}
+.highlight-box {
+    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+    padding: 20px;
+    border-radius: 10px;
+    color: white;
+}
+"""
+
+# Build the interface
+with gr.Blocks(css=custom_css, title="🎧 Audio Reasoning Explorer", theme=gr.themes.Soft()) as demo:
+    
+    # Header
+    gr.Markdown("""
+    <div style="text-align: center; padding: 20px;">
+        <h1>🎧 Audio Reasoning & Step-Audio-R1 Explorer</h1>
+        <p style="font-size: 18px; color: #666;">
+            Interactive guide to understanding how AI learns to think about sound
+        </p>
+    </div>
+    """)
+    
+    # Main tabs
+    with gr.Tabs():
+        
+        # Tab 1: Introduction
+        with gr.TabItem("🏠 Introduction", id=0):
+            gr.Markdown(INTRO_CONTENT)
+        
+        # Tab 2: Audio Reasoning Types
+        with gr.TabItem("🧠 Reasoning Types", id=1):
+            gr.Markdown("## 🧠 Types of Audio Reasoning\n\nSelect a reasoning type to learn more:")
+            
+            with gr.Row():
+                with gr.Column(scale=1):
+                    reasoning_dropdown = gr.Dropdown(
+                        choices=list(REASONING_TYPES.keys()),
+                        label="Select Reasoning Type",
+                        value="Factual Reasoning"
+                    )
+                    
+                    gr.Markdown("### Quick Overview")
+                    for rtype, info in REASONING_TYPES.items():
+                        gr.Markdown(f"{info['emoji']} **{rtype}**: {info['description']}")
+                
+                with gr.Column(scale=2):
+                    reasoning_output = gr.Markdown(
+                        value=get_reasoning_type_info("Factual Reasoning")
+                    )
+            
+            reasoning_dropdown.change(
+                fn=get_reasoning_type_info,
+                inputs=[reasoning_dropdown],
+                outputs=[reasoning_output]
+            )
+        
+        # Tab 3: The Problem
+        with gr.TabItem("🚫 The Problem", id=2):
+            gr.Markdown(PROBLEM_CONTENT)
+        
+        # Tab 4: MGRD Solution
+        with gr.TabItem("🔬 MGRD Solution", id=3):
+            gr.Markdown(MGRD_CONTENT)
+        
+        # Tab 5: Architecture
+        with gr.TabItem("🏗️ Architecture", id=4):
+            gr.Markdown(ARCHITECTURE_CONTENT)
+        
+        # Tab 6: Benchmarks
+        with gr.TabItem("📊 Benchmarks", id=5):
+            gr.Markdown(BENCHMARK_DATA)
+            gr.Markdown(create_comparison_chart())
+        
+        # Tab 7: Interactive Demo
+        with gr.TabItem("🎮 Interactive Demo", id=6):
+            gr.Markdown("""
+            ## 🎮 Interactive Audio Reasoning Demo
+            
+            See how Step-Audio-R1 would analyze different audio scenarios!
+            
+            *Note: This is a simulation showing the reasoning process. 
+            The actual model processes real audio input.*
+            """)
+            
+            with gr.Row():
+                with gr.Column(scale=1):
+                    scenario_dropdown = gr.Dropdown(
+                        choices=[
+                            "Customer Service Call",
+                            "Meeting Recording", 
+                            "Podcast Episode",
+                            "Music Analysis"
+                        ],
+                        label="Select Audio Scenario",
+                        value="Customer Service Call"
+                    )
+                    
+                    analyze_btn = gr.Button("🔍 Analyze Scenario", variant="primary")
+                    
+                    gr.Markdown("""
+                    ### What This Shows
+                    
+                    Each scenario demonstrates:
+                    1. **Acoustic analysis** - What the model "hears"
+                    2. **Reasoning process** - Step-by-step thinking
+                    3. **Final output** - Actionable insights
+                    
+                    This is the power of **audio reasoning**!
+                    """)
+                
+                with gr.Column(scale=2):
+                    demo_output = gr.Markdown(
+                        value=generate_demo_reasoning("Customer Service Call")
+                    )
+            
+            analyze_btn.click(
+                fn=generate_demo_reasoning,
+                inputs=[scenario_dropdown],
+                outputs=[demo_output]
+            )
+        
+        # Tab 8: Applications
+        with gr.TabItem("🚀 Applications", id=7):
+            gr.Markdown(APPLICATIONS_CONTENT)
+        
+        # Tab 9: Resources
+        with gr.TabItem("📚 Resources", id=8):
+            gr.Markdown(RESOURCES_CONTENT)
+    
+    # Footer
+    gr.Markdown("""
+    ---
+    <div style="text-align: center; padding: 20px; color: #666;">
+        <p>Created by <strong>Mehmet Tuğrul Kaya</strong> | 
+        <a href="https://github.com/mtkaya">GitHub</a> | 
+        <a href="https://huggingface.co/tugrulkaya">HuggingFace</a></p>
+        <p>🎧 Sound Speaks, AI Listens and Thinks 🧠</p>
+    </div>
+    """)
+
+# Launch
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1 @@
+gradio>=4.0.0