Upload folder using huggingface_hub

README.md

@@ -1,33 +1,33 @@
----
-title: AnomalyMachine-50K Demo
-colorFrom: red
-colorTo: gray
-sdk: gradio
-sdk_version: 4.44.0
-app_file: app.py
-pinned: true
-license: cc-by-4.0
----
-
-# AnomalyMachine-50K Demo
-
-Interactive demo for the AnomalyMachine-50K synthetic industrial machine sound anomaly detection dataset.
-
-## Features
-
-- **Anomaly Detection**: Upload audio or record live to detect anomalies in machine sounds
-- **Dataset Exploration**: Browse example spectrograms for each machine type
-- **Visual Analysis**: Compare input audio against reference normal samples
-
-## Dataset
-
-- **50,000** synthetic audio clips
-- **6** machine types (fan, pump, compressor, conveyor_belt, electric_motor, valve)
-- **5** anomaly types (bearing_fault, imbalance, cavitation, overheating, obstruction)
-- **10 seconds** per clip at **22,050 Hz**
-
-[View Dataset →](https://huggingface.co/datasets/AnomalyMachine-50K)
-
-## License
-
-CC-BY-4.0
+---
+title: AnomalyMachine-50K Demo
+colorFrom: red
+colorTo: gray
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: true
+license: cc-by-4.0
+---
+
+# AnomalyMachine-50K Demo
+
+Interactive demo for the AnomalyMachine-50K synthetic industrial machine sound anomaly detection dataset.
+
+## Features
+
+- **Anomaly Detection**: Upload audio or record live to detect anomalies in machine sounds
+- **Dataset Exploration**: Browse example spectrograms for each machine type
+- **Visual Analysis**: Compare input audio against reference normal samples
+
+## Dataset
+
+- **50,000** synthetic audio clips
+- **6** machine types (fan, pump, compressor, conveyor_belt, electric_motor, valve)
+- **5** anomaly types (bearing_fault, imbalance, cavitation, overheating, obstruction)
+- **10 seconds** per clip at **22,050 Hz**
+
+[View Dataset →](https://huggingface.co/datasets/AnomalyMachine-50K)
+
+## License
+
+CC-BY-4.0

deploy_spaces.py

@@ -8,15 +8,74 @@ from pathlib import Path
 from dotenv import load_dotenv
 from huggingface_hub import HfApi, upload_folder
 
-# Load environment variables
-load_dotenv()
 
-
-def ensure_hf_token() -> str:
+def ensure_hf_token(project_root: Path) -> str:
     """Load the Hugging Face token from environment variables."""
+    # Try loading from project root .env file first
+    env_file = project_root / ".env"
+    env_loaded = False
+    
+    if env_file.exists():
+        print(f"Loading .env from: {env_file}")
+        load_dotenv(env_file, override=True)
+        env_loaded = True
+    else:
+        # Fallback: try current directory
+        print("Project root .env not found, trying current directory...")
+        load_dotenv()
+    
+    # Also try spaces_demo/.env if it exists
+    spaces_env = project_root / "spaces_demo" / ".env"
+    if spaces_env.exists():
+        print(f"Also loading .env from: {spaces_env}")
+        load_dotenv(spaces_env, override=True)
+    
+    # Check environment variable
     token = os.getenv("HF_TOKEN")
+    
     if not token:
+        print("\n" + "="*60)
+        print("ERROR: HF_TOKEN not found!")
+        print("="*60)
+        print(f"\nChecked locations:")
+        print(f"  1. {env_file} {'✓' if env_file.exists() else '✗ (not found)'}")
+        print(f"  2. {spaces_env} {'✓' if spaces_env.exists() else '✗ (not found)'}")
+        print(f"  3. Environment variable: {'✓' if os.getenv('HF_TOKEN') else '✗ (not set)'}")
+        print("\nTo fix this:")
+        print("1. Create or edit .env file in the project root:")
+        print(f"   {env_file}")
+        print("2. Add your Hugging Face token (must start with 'hf_'):")
+        print("   HF_TOKEN=hf_your_actual_token_here")
+        print("\nOr set it as an environment variable:")
+        print("   $env:HF_TOKEN='hf_your_token'  # PowerShell")
+        print("   export HF_TOKEN='hf_your_token'  # Bash")
+        print("\nGet your token from: https://huggingface.co/settings/tokens")
+        print("="*60 + "\n")
         raise EnvironmentError("HF_TOKEN is not set in environment or .env file.")
+    
+    # Remove any quotes or whitespace
+    token = token.strip().strip('"').strip("'").strip()
+    
+    # Show first few characters for debugging (without exposing full token)
+    token_preview = token[:10] + "..." if len(token) > 10 else token[:len(token)]
+    print(f"Token loaded: {token_preview} (length: {len(token)})")
+    
+    # Basic validation
+    if not token.startswith("hf_"):
+        print("\n" + "="*60)
+        print("ERROR: Invalid token format!")
+        print("="*60)
+        print(f"\nYour token starts with: '{token[:5]}...'")
+        print("But it should start with: 'hf_'")
+        print("\nCommon issues:")
+        print("1. Token might have extra spaces or quotes")
+        print("2. Token might be incomplete")
+        print("3. You might be using an old token format")
+        print("\nGet a new token from: https://huggingface.co/settings/tokens")
+        print("Make sure to copy the FULL token (it should start with 'hf_')")
+        print("="*60 + "\n")
+        raise ValueError("HF_TOKEN must start with 'hf_'. Please check your token.")
+    
     return token
 
 
@@ -58,7 +117,20 @@ def deploy_space(
     private: bool = False,
 ) -> None:
     """Deploy the demo to Hugging Face Spaces."""
-    api = HfApi()
+    api = HfApi(token=token)
+
+    # Verify token works by checking user info
+    try:
+        user_info = api.whoami(token=token)
+        print(f"Authenticated as: {user_info.get('name', 'Unknown')}")
+    except Exception as e:
+        print(f"\n❌ Authentication failed: {e}")
+        print("\nTroubleshooting:")
+        print("1. Your HF_TOKEN may be invalid or expired")
+        print("2. Get a new token at: https://huggingface.co/settings/tokens")
+        print("3. Make sure the token has 'write' permissions")
+        print("4. Update your .env file with the new token")
+        raise
 
     # Check if repo exists
     try:
@@ -66,13 +138,25 @@ def deploy_space(
         print(f"Space '{repo_id}' already exists. Updating...")
     except Exception:
         print(f"Creating new Space '{repo_id}'...")
-        api.create_repo(
-            repo_id=repo_id,
-            token=token,
-            repo_type="space",
-            exist_ok=True,
-            space_sdk="gradio",
-        )
+        try:
+            api.create_repo(
+                repo_id=repo_id,
+                token=token,
+                repo_type="space",
+                exist_ok=True,
+                space_sdk="gradio",
+            )
+            print(f"✅ Space created successfully!")
+        except Exception as create_error:
+            print(f"\n❌ Error creating Space: {create_error}")
+            print("\nTroubleshooting:")
+            print("1. Verify your HF_TOKEN is valid and not expired")
+            print("2. Check that the token has 'write' permissions")
+            print("3. Get a new token at: https://huggingface.co/settings/tokens")
+            username = repo_id.split('/')[0]
+            print(f"4. Make sure your username '{username}' is correct")
+            print(f"5. Check if you have permission to create Spaces under '{username}'")
+            raise
 
     # Copy example audio files from generated dataset
     examples_dir = spaces_demo_dir / "examples"
@@ -82,6 +166,28 @@ def deploy_space(
     else:
         print(f"Warning: Output directory not found at {output_dir}. Skipping example files.")
 
+    # Ensure README.md doesn't have emoji field (fix encoding issues)
+    readme_path = spaces_demo_dir / "README.md"
+    if readme_path.exists():
+        print("Ensuring README.md has correct format...")
+        with open(readme_path, "r", encoding="utf-8") as f:
+            content = f.read()
+        
+        # Remove emoji line if it exists (to avoid encoding issues)
+        lines = content.split("\n")
+        filtered_lines = []
+        for line in lines:
+            if line.strip().startswith("emoji:"):
+                print(f"  Removing emoji line: {line.strip()}")
+                continue
+            filtered_lines.append(line)
+        
+        # Write back without emoji
+        content_fixed = "\n".join(filtered_lines)
+        with open(readme_path, "w", encoding="utf-8", newline="\n") as f:
+            f.write(content_fixed)
+        print("README.md cleaned and saved with UTF-8 encoding.")
+
     # Upload all files in spaces_demo directory
     print(f"Uploading files from {spaces_demo_dir}...")
     upload_folder(
@@ -129,11 +235,12 @@ def main() -> None:
     # Determine paths
     script_dir = Path(__file__).resolve().parent
     spaces_demo_dir = script_dir
+    project_root = script_dir.parent
     output_dir = Path(args.output_dir).resolve()
     if not output_dir.is_absolute():
-        output_dir = script_dir.parent / args.output_dir
+        output_dir = project_root / args.output_dir
 
-    token = ensure_hf_token()
+    token = ensure_hf_token(project_root)
 
     deploy_space(
         spaces_demo_dir=spaces_demo_dir,