Tests fixed and added ruff and updated README.md

Author: sumerjoshi

README.md

@@ -101,3 +101,45 @@ python predict.py --folder path/to/audio/files --model model/saved_models/your_m
 - Training data should be organized in the `data/train/` directory
 - Model checkpoints are saved in `model/saved_models/`
 - The project is installed as a Python package for proper import handling
+
+## Code Quality
+
+This project uses Ruff for both linting and formatting Python code. Ruff is a fast Python linter and formatter written in Rust.
+
+### Using Ruff
+
+1. Install Ruff (it's already included in the dev dependencies):
+```bash
+# Using pip (recommended if you want to use your existing virtual environment)
+pip install -e ".[dev]"
+
+# OR using uv pip (if you want to use uv but keep your current virtual environment)
+uv pip install -e ".[dev]"
+
+# Note: Do NOT use 'uv venv' unless you want to create a new virtual environment
+# with pyenv. If you want to use uv while keeping your current environment,
+# use 'uv pip' instead.
+```
+
+2. Format your code:
+```bash
+ruff format .
+```
+
+3. Lint your code:
+```bash
+ruff check .
+```
+
+4. Fix linting issues automatically:
+```bash
+ruff check --fix .
+```
+
+The Ruff configuration is in `pyproject.toml`. Currently, it:
+- Uses a line length of 88 characters (same as Black)
+- Targets Python 3.9
+- Enables pycodestyle (`E`) and Pyflakes (`F`) rules by default
+- Ignores line length violations (`E501`)
+
+You can customize the Ruff configuration by modifying the `[tool.ruff]` section in `pyproject.toml`.

dataset/__init__.py

@@ -1 +1 @@
-"""Dataset package for audio processing AI.""" 
+"""Dataset package for audio processing AI."""

dataset/ai_audio_dataset.py

@@ -5,23 +5,24 @@
 from typing import Tuple
 from zipfile import ZipFile
 
+
 class AIAudioDataset(torch.utils.data.Dataset):
     def __init__(self, root_dir, sample_rate=16000, duration=10.0) -> None:
         """
         Args:
-            root_dir: str  Path to .mp3 and .wav files to create the training. 
+            root_dir: str  Path to .mp3 and .wav files to create the training.
             sample_rate: int  set to 16khz for training
             duration: float   set to 10 seconds for sampling
         """
-        self.paths = list(Path(root_dir).rglob("*.wav")) + list(Path(root_dir).rglob("*.mp3"))
+        self.paths = list(Path(root_dir).rglob("*.wav")) + list(
+            Path(root_dir).rglob("*.mp3")
+        )
         self.sample_rate = sample_rate
         self.duration = duration
         self.audio_len = int(sample_rate * duration)
 
-    
     def __len__(self) -> int:
         return len(self.paths)
-    
 
     def __getitem__(self, idx) -> Tuple[torch.Tensor, torch.Tensor]:
         path = self.paths[idx]
@@ -31,7 +32,7 @@ def __getitem__(self, idx) -> Tuple[torch.Tensor, torch.Tensor]:
             waveform = torchaudio.transforms.Resample(sr, self.sample_rate)(waveform)
 
         if waveform.shape[0] > 1:
-            waveform = waveform.mean(dim=0,keepdim=True)
+            waveform = waveform.mean(dim=0, keepdim=True)
 
         total_len = waveform.shape[1]
 
@@ -40,18 +41,18 @@ def __getitem__(self, idx) -> Tuple[torch.Tensor, torch.Tensor]:
             waveform = torch.nn.functional.pad(waveform, (0, pad_len))
         else:
             start = random.randint(0, total_len - self.audio_len)
-            waveform = waveform[:, start:start + self.audio_len]
+            waveform = waveform[:, start : start + self.audio_len]
 
         mel_spec = torchaudio.transforms.MelSpectrogram(
             sample_rate=self.sample_rate,
             n_fft=1024,
             hop_length=320,
             n_mels=64,
             f_min=50,
-            f_max=8000
+            f_max=8000,
         )(waveform)
 
         logmel = torch.log(mel_spec + 1e-6)
 
         label = 1 if "ai" in str(path).lower() else 0
-        return logmel.squeeze(0), torch.tensor(label)
+        return logmel.squeeze(0), torch.tensor(label)

inference/__init__.py

@@ -1 +1 @@
-"""Inference package for audio processing AI.""" 
+"""Inference package for audio processing AI."""

model/__init__.py

@@ -1 +1 @@
-"""Model package for audio processing AI.""" 
+"""Model package for audio processing AI."""