tasks/audio.py

from fastapi import APIRouter
from datetime import datetime
from datasets import load_dataset
from sklearn.metrics import accuracy_score
import os
import joblib
import librosa
import numpy as np

from .utils.evaluation import AudioEvaluationRequest
from .utils.emissions import tracker, clean_emissions_data, get_space_info

from dotenv import load_dotenv
load_dotenv()

router = APIRouter()

DESCRIPTION = "Model 2 : Random Forest audio classification"
ROUTE = "/audio"


@router.post(ROUTE, tags=["Audio Task"],
             description=DESCRIPTION)
async def evaluate_audio(request: AudioEvaluationRequest):
    """
    Evaluate audio classification for rainforest sound detection.

    Current Model: Random Baseline
    - Makes random predictions from the label space (0-1)
    - Used as a baseline for comparison
    """
    # Get space info
    username, space_url = get_space_info()

    # Define the label mapping
    LABEL_MAPPING = {
        "chainsaw": 0,
        "environment": 1
    }
    # Load and prepare the dataset
    # Because the dataset is gated, we need to use the HF_TOKEN environment variable to authenticate
    dataset = load_dataset(request.dataset_name, token=os.getenv("HF_TOKEN"))

    # Split dataset
    train_test = dataset["train"]
    test_dataset = dataset["test"]

    # Start tracking emissions
    tracker.start()
    tracker.start_task("inference")

    # --------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE CODE HERE
    # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
    # --------------------------------------------------------------------------------------------
    # data formatting

    def preprocess(dataset):
        features = []
        for row in dataset:
            # Load the audio file and resample it
            target_sr = 6000
            audio = row['audio']['array']
            audio = librosa.resample(audio, orig_sr=12000, target_sr=target_sr)

            # Extract MFCC features
            mfccs = librosa.feature.mfcc(y=audio, sr=target_sr, n_mfcc=10)
            mfccs_scaled = np.mean(mfccs.T, axis=0)

            # Append features and labels
            features.append(mfccs_scaled)

        return np.array(features)

    X_test = preprocess(test_dataset)

    classification_model = joblib.load("./models/audio_classification_rf.pkl")

    predictions = classification_model.predict(X_test)
    true_labels = test_dataset["label"]

    # --------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE STOPS HERE
    # --------------------------------------------------------------------------------------------

    # Stop tracking emissions
    emissions_data = tracker.stop_task()

    # Calculate accuracy
    accuracy = accuracy_score(true_labels, predictions)

    # Prepare results dictionary
    results = {
        "username": username,
        "space_url": space_url,
        "submission_timestamp": datetime.now().isoformat(),
        "model_description": DESCRIPTION,
        "accuracy": float(accuracy),
        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
        "emissions_gco2eq": emissions_data.emissions * 1000,
        "emissions_data": clean_emissions_data(emissions_data),
        "api_route": ROUTE,
        "dataset_config": {
            "dataset_name": request.dataset_name,
            "test_size": request.test_size,
            "test_seed": request.test_seed
        }
    }
    return results