from fastapi import APIRouter from datetime import datetime from datasets import load_dataset from sklearn.metrics import accuracy_score import random import os import librosa import joblib import numpy as np import lightgbm 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 = "Random Baseline" 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 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. #-------------------------------------------------------------------------------------------- def preprocess_data(row, sr): new_row = librosa.resample(row['audio']['array'], orig_sr=row['audio']['sampling_rate'], target_sr=sr) new_row = np.pad(new_row, (0, 3 * sr - len(new_row)), 'constant') new_row = librosa.feature.mfcc(y=new_row, sr=sr, n_mfcc=10) return new_row.flatten() test_list_mfcc = np.vstack([preprocess_data(row, 12000) for row in test_dataset]) model_filename = "lightgbm_10_mfcc.pkl" clf = joblib.load(model_filename) true_labels = test_dataset["label"] predictions = clf.predict(test_list_mfcc) #-------------------------------------------------------------------------------------------- # 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