### Install DeepRhythm using pip

Source: https://github.com/bleugreen/deeprhythm/blob/main/README.md

Install the DeepRhythm package using pip. Ensure Python and pip are installed on your system.

```bash
pip install deeprhythm
```

--------------------------------

### Python Inference from Loaded Audio

Source: https://github.com/bleugreen/deeprhythm/blob/main/README.md

Predict tempo from audio data already loaded into memory, for example, using librosa. This allows for pre-processing before tempo prediction.

```python
import librosa
from deeprhythm import DeepRhythmPredictor

model = DeepRhythmPredictor()

audio, sr = librosa.load('path/to/song.mp3')

# ... other steps for processing the audio ...

tempo = model.predict_from_audio(audio, sr)

# to include confidence
tempo, confidence = model.predict_from_audio(audio, sr, include_confidence=True)

print(f"Predicted Tempo: {tempo} BPM")
```

--------------------------------

### CLI Batch Inference for a Directory

Source: https://github.com/bleugreen/deeprhythm/blob/main/README.md

Predict the tempo for all songs within a specified directory. Results are saved to a JSONL file. Flags allow specifying output path, confidence scores, device, and quiet logging.

```bash
python -m deeprhythm.batch_infer /path/to/dir
# Flags:
# -o output_path.jsonl - provide a custom output path (default 'batch_results.jsonl`)
# -c, --conf - include confidence scores
# -d, --device [cuda/cpu/mps] - specify model device
# -q, --quiet - doesn't print status / logs
```

--------------------------------

### CLI Inference for a Single Song

Source: https://github.com/bleugreen/deeprhythm/blob/main/README.md

Predict the tempo of a single audio file using the command-line interface. Use the -cq flags to include confidence scores and quiet output.

```bash
python -m deeprhythm.infer /path/to/song.wav -cq
> ([bpm], [confidence])
```

--------------------------------

### Python Inference for a Single Song

Source: https://github.com/bleugreen/deeprhythm/blob/main/README.md

Predict the tempo of an audio file using the DeepRhythmPredictor class in Python. The predict method can optionally return confidence scores.

```python
from deeprhythm import DeepRhythmPredictor

model = DeepRhythmPredictor()

tempo = model.predict('path/to/song.mp3')

# to include confidence
tempo, confidence = model.predict('path/to/song.mp3', include_confidence=True)

print(f"Predicted Tempo: {tempo} BPM")
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.