Upload folder using huggingface_hub

dataset.py

@@ -0,0 +1,141 @@
+import os
+import random
+
+import numpy as np
+import pandas as pd
+import torch
+from audiomentations import (
+    Compose,
+    AddGaussianNoise,
+    TimeStretch,
+    PitchShift,
+    Shift,
+    Gain
+)
+from datasets import load_dataset, Audio
+from transformers import AutoFeatureExtractor
+
+# 랜덤 시드 고정
+random.seed(442)
+np.random.seed(442)
+
+# 데이터셋에서 삭제할 (필요 없는)columns
+remove_columns = ['filename', 'esc10', 'audio']
+# Google AudioSet를 pretrained한 모델과 특징 추출기를 불러옴
+model_name = "MIT/ast-finetuned-audioset-10-10-0.4593"
+
+# HuggingFace에 저장된 ashraq/esc50 데이터셋을 불러옴
+esc50_dataset = load_dataset('ashraq/esc50')
+
+# 특징 추출기
+feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+
+
+def split_by_fold(dataset_split, test_fold=1):
+    train_dataset = dataset_split.filter(lambda df: df['fold'] != test_fold)
+    val_dataset = dataset_split.filter(lambda df: df['fold'] == test_fold)
+    print(f"학습 데이터셋: {train_dataset.shape}, 검증 데이터셋: {val_dataset.shape}")
+    return train_dataset, val_dataset
+
+
+# 체크포인트가 있다면 "./output" 내의 checkpoint 디렉토리를 자동으로 불러오기
+def get_latest_checkpoint(output_dir):
+    if os.path.exists(output_dir):
+        checkpoints = [os.path.join(output_dir, d) for d in os.listdir(output_dir) if d.startswith('checkpoint') and os.path.isdir(os.path.join(output_dir, d))]
+        if checkpoints:
+            # 정렬 후 마지막 체크포인트 선택
+            return sorted(checkpoints)[-1]
+
+
+def preprocess_function(data, apply_augmentation=False):
+    raw = data['audio']['array']
+    sr = data['audio']['sampling_rate']
+
+    waveform = torch.tensor(raw, dtype=torch.float32)
+
+    # 학습 시 증강 적용 여부
+    if apply_augmentation:
+        waveform, sr = advanced_augment_audio_moderate(waveform, sr)
+        # 증강 후 waveform을 numpy 배열로 변환 (특징 추출기가 numpy 입력을 필요로 할 경우)
+        raw = waveform.squeeze(0).numpy()
+    else:
+        raw = waveform.squeeze(0).numpy()
+
+    inputs = feature_extractor(raw, sampling_rate=sr, return_tensors='pt')
+    # inputs['input_values'] = inputs['input_values'].squeeze(0).numpy()
+
+    return inputs
+
+
+def get_moderate_augmentation_pipeline(sample_rate):
+    # # RoomSimulator 효과는 IR(Impulse Response) 파일이 필요합니다.
+    # # 실제 환경의 방음 특성을 반영한 IR 파일을 사용하세요.
+    # ir_path = "your_ir_file.wav"  # IR 파일 경로를 지정합니다.
+    #
+    # # Windows 환경에서 RoomSimulator가 동작하지 않을 경우 None으로 처리합니다.
+    # room_simulator = RoomSimulator(ir_path=ir_path, p=0.3) if platform.system() != "Windows" else None
+
+    # 여러 효과들을 Compose로 묶어줍니다.
+    # 각 트랜스폼은 실제 환경에서 너무 극단적이지 않은 수준으로 적용합니다.
+    transforms = [
+        # 배경 잡음을 약하게 추가 (실제 녹음된 환경의 미세한 잡음 모방)
+        AddGaussianNoise(min_amplitude=0.001, max_amplitude=0.005, p=0.5),
+        # 약간의 시간 변형 (너무 심하게 적용하면 오디오 특징이 깨질 수 있으므로 미세하게)
+        TimeStretch(min_rate=0.95, max_rate=1.05, p=0.5),
+        # 피치를 약간 변화시켜, 자연스러운 음높이 차이 모방 (±1 반음 정도)
+        PitchShift(min_semitones=-1, max_semitones=1, p=0.5),
+        # 오디오 신호의 시작이나 끝을 약간 이동 (전체 길이의 5~10% 정도)
+        Shift(min_shift=-0.1, max_shift=0.1, p=0.5),
+        # 실제 방의 잔향 효과를 반영 (IR 파일이 있다면 자연스러운 리버브 효과 적용)
+        # room_simulator,
+        # 볼륨을 약간 조절하여 녹음 조건의 차이를 반영
+        Gain(min_gain_db=-2.0, max_gain_db=2.0, p=0.5),
+    ]
+    # None인 효과는 필터링합니다.
+    transforms = [t for t in transforms if t is not None]
+    return Compose(transforms, p=1.0)
+
+
+def advanced_augment_audio_moderate(waveform, sample_rate):
+    """
+    입력된 waveform (torch.Tensor, shape: [1, samples])에 대해
+    실제 환경을 적당히 모방하는 증강을 적용합니다.
+    """
+    # waveform을 numpy array (모노 채널)로 변환합니다.
+    np_waveform = waveform.squeeze(0).numpy()
+
+    # 증강 파이프라인을 얻습니다.
+    augmentation_pipeline = get_moderate_augmentation_pipeline(sample_rate)
+
+    # 증강 효과 적용: np_waveform는 1차원 numpy array라고 가정합니다.
+    augmented_np_waveform = augmentation_pipeline(np_waveform, sample_rate=sample_rate)
+
+    # numpy array를 다시 torch.Tensor로 변환 후 (채널 차원 추가) 반환합니다.
+    augmented_waveform = torch.tensor(augmented_np_waveform, dtype=torch.float32).unsqueeze(0)
+    return augmented_waveform, sample_rate
+
+
+def load_dataset_esc50(apply_augmentation=False):
+    esc50_dataloader = esc50_dataset['train']
+    esc50_dataloader = esc50_dataloader.cast_column('audio', Audio(sampling_rate=16000))
+    # print(esc50_dataloader.shape)
+
+    input_values = esc50_dataloader.map(
+        lambda data: preprocess_function(data, apply_augmentation)
+    )
+    # print(f'특징 추출기 적용 후: {input_values}')
+
+    # # 폴드 설정
+    df = pd.DataFrame(esc50_dataloader)
+    folds = df.query('fold >= 1')['fold'].drop_duplicates().tolist()
+
+    # 최종적인 dataset 설정
+    # esc50_dataloader = esc50_dataloader.add_column(name='input_values', column=input_values)
+    input_values = input_values.remove_columns(remove_columns)
+    # 학습의 원할함을 위해 target을 명시적으로 label로 변경
+    input_values = input_values.rename_column('target', 'label')
+
+    return input_values, folds
+
+
+# load_dataset_esc50()

export_onnx.py

@@ -0,0 +1,33 @@
+from optimum.onnxruntime import ORTModelForSequenceClassification
+from transformers import AutoFeatureExtractor, AutoTokenizer
+
+def export_audio_model_to_onnx(
+    model_dir: str,
+    save_dir: str,
+):
+    # 1) ONNX export: export=True 옵션만 주면 internal export script가 실행됩니다.
+    ort_model = ORTModelForSequenceClassification.from_pretrained(
+        model_dir,
+        export=True,                     # 이 옵션이 ONNX로 내보내게 합니다
+        file_name="model.onnx",          # (선택) 저장될 ONNX 파일 이름
+    )
+
+    # 2) 토크나이저/특징추출기도 함께 저장
+    #    AST는 feature_extractor만 있으면 추론 가능합니다.
+    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+    feature_extractor = AutoFeatureExtractor.from_pretrained(model_dir)
+
+    # 3) 출력 디렉토리에 모두 저장
+    ort_model.save_pretrained(save_dir)
+    tokenizer.save_pretrained(save_dir)
+    feature_extractor.save_pretrained(save_dir)
+    print(f"✅ ONNX 모델과 tokenizer/feature_extractor를 '{save_dir}'에 저장했습니다.")
+
+if __name__ == "__main__":
+    import argparse
+    p = argparse.ArgumentParser()
+    p.add_argument("--model_dir", required=True, help="학습된 HF 모델 디렉토리")
+    p.add_argument("--save_dir", required=True, help="ONNX 포함 결과를 저장할 디렉토리")
+    args = p.parse_args()
+
+    export_audio_model_to_onnx(args.model_dir, args.save_dir)

functions.py

@@ -0,0 +1,66 @@
+from typing import Tuple, List, Dict, Any
+
+import evaluate
+import numpy as np
+import pandas as pd
+from transformers import ASTForAudioClassification, Trainer, TrainingArguments
+
+from dataset import load_dataset_esc50
+
+
+def squeeze_func(batch: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    Remove the extra dimension from input_values.
+    """
+    batch['input_values'] = np.asarray(batch['input_values']).squeeze(0)
+    return batch
+
+
+def prepare_datasets(apply_augmentation: bool) -> Tuple[Any, List[int]]:
+    """
+    Load and preprocess the ESC-50 dataset.
+    """
+    dataset, folds = load_dataset_esc50(apply_augmentation=apply_augmentation)
+    return dataset.map(squeeze_func), folds
+
+
+def get_model(model_name: str) -> ASTForAudioClassification:
+    """
+    Load the AST audio classification model with SDPA.
+    """
+    return ASTForAudioClassification.from_pretrained(
+        model_name,
+        attn_implementation="sdpa"
+    )
+
+
+def make_trainer(
+    model: ASTForAudioClassification,
+    train_dataset: Any,
+    eval_dataset: Any,
+    args: TrainingArguments
+) -> Trainer:
+    """
+    Build and return a HuggingFace Trainer instance.
+    """
+    metric = evaluate.load('accuracy')
+
+    def compute_metrics(pred):
+        logits, labels = pred
+        return metric.compute(predictions=np.argmax(logits, axis=-1), references=labels)
+
+    return Trainer(
+        model=model,
+        args=args,
+        train_dataset=train_dataset,
+        eval_dataset=eval_dataset,
+        compute_metrics=compute_metrics,
+    )
+
+
+def save_results(results: List[Dict[str, Any]], csv_path: str) -> None:
+    """
+    Save the experiment results to a CSV file.
+    """
+    pd.DataFrame(results).to_csv(csv_path, index=False)
+    print(f"Results saved to {csv_path}")

output/augmented_esc50/all_results.json

@@ -0,0 +1,8 @@
+{
+    "test_accuracy": 0.9835,
+    "test_loss": 0.07399206608533859,
+    "test_model_preparation_time": 0.1745,
+    "test_runtime": 110.5501,
+    "test_samples_per_second": 18.091,
+    "test_steps_per_second": 2.261
+}

output/augmented_esc50/config.json

@@ -0,0 +1,1082 @@
+{
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Speech",
+    "1": "Male speech, man speaking",
+    "2": "Female speech, woman speaking",
+    "3": "Child speech, kid speaking",
+    "4": "Conversation",
+    "5": "Narration, monologue",
+    "6": "Babbling",
+    "7": "Speech synthesizer",
+    "8": "Shout",
+    "9": "Bellow",
+    "10": "Whoop",
+    "11": "Yell",
+    "12": "Battle cry",
+    "13": "Children shouting",
+    "14": "Screaming",
+    "15": "Whispering",
+    "16": "Laughter",
+    "17": "Baby laughter",
+    "18": "Giggle",
+    "19": "Snicker",
+    "20": "Belly laugh",
+    "21": "Chuckle, chortle",
+    "22": "Crying, sobbing",
+    "23": "Baby cry, infant cry",
+    "24": "Whimper",
+    "25": "Wail, moan",
+    "26": "Sigh",
+    "27": "Singing",
+    "28": "Choir",
+    "29": "Yodeling",
+    "30": "Chant",
+    "31": "Mantra",
+    "32": "Male singing",
+    "33": "Female singing",
+    "34": "Child singing",
+    "35": "Synthetic singing",
+    "36": "Rapping",
+    "37": "Humming",
+    "38": "Groan",
+    "39": "Grunt",
+    "40": "Whistling",
+    "41": "Breathing",
+    "42": "Wheeze",
+    "43": "Snoring",
+    "44": "Gasp",
+    "45": "Pant",
+    "46": "Snort",
+    "47": "Cough",
+    "48": "Throat clearing",
+    "49": "Sneeze",
+    "50": "Sniff",
+    "51": "Run",
+    "52": "Shuffle",
+    "53": "Walk, footsteps",
+    "54": "Chewing, mastication",
+    "55": "Biting",
+    "56": "Gargling",
+    "57": "Stomach rumble",
+    "58": "Burping, eructation",
+    "59": "Hiccup",
+    "60": "Fart",
+    "61": "Hands",
+    "62": "Finger snapping",
+    "63": "Clapping",
+    "64": "Heart sounds, heartbeat",
+    "65": "Heart murmur",
+    "66": "Cheering",
+    "67": "Applause",
+    "68": "Chatter",
+    "69": "Crowd",
+    "70": "Hubbub, speech noise, speech babble",
+    "71": "Children playing",
+    "72": "Animal",
+    "73": "Domestic animals, pets",
+    "74": "Dog",
+    "75": "Bark",
+    "76": "Yip",
+    "77": "Howl",
+    "78": "Bow-wow",
+    "79": "Growling",
+    "80": "Whimper (dog)",
+    "81": "Cat",
+    "82": "Purr",
+    "83": "Meow",
+    "84": "Hiss",
+    "85": "Caterwaul",
+    "86": "Livestock, farm animals, working animals",
+    "87": "Horse",
+    "88": "Clip-clop",
+    "89": "Neigh, whinny",
+    "90": "Cattle, bovinae",
+    "91": "Moo",
+    "92": "Cowbell",
+    "93": "Pig",
+    "94": "Oink",
+    "95": "Goat",
+    "96": "Bleat",
+    "97": "Sheep",
+    "98": "Fowl",
+    "99": "Chicken, rooster",
+    "100": "Cluck",
+    "101": "Crowing, cock-a-doodle-doo",
+    "102": "Turkey",
+    "103": "Gobble",
+    "104": "Duck",
+    "105": "Quack",
+    "106": "Goose",
+    "107": "Honk",
+    "108": "Wild animals",
+    "109": "Roaring cats (lions, tigers)",
+    "110": "Roar",
+    "111": "Bird",
+    "112": "Bird vocalization, bird call, bird song",
+    "113": "Chirp, tweet",
+    "114": "Squawk",
+    "115": "Pigeon, dove",
+    "116": "Coo",
+    "117": "Crow",
+    "118": "Caw",
+    "119": "Owl",
+    "120": "Hoot",
+    "121": "Bird flight, flapping wings",
+    "122": "Canidae, dogs, wolves",
+    "123": "Rodents, rats, mice",
+    "124": "Mouse",
+    "125": "Patter",
+    "126": "Insect",
+    "127": "Cricket",
+    "128": "Mosquito",
+    "129": "Fly, housefly",
+    "130": "Buzz",
+    "131": "Bee, wasp, etc.",
+    "132": "Frog",
+    "133": "Croak",
+    "134": "Snake",
+    "135": "Rattle",
+    "136": "Whale vocalization",
+    "137": "Music",
+    "138": "Musical instrument",
+    "139": "Plucked string instrument",
+    "140": "Guitar",
+    "141": "Electric guitar",
+    "142": "Bass guitar",
+    "143": "Acoustic guitar",
+    "144": "Steel guitar, slide guitar",
+    "145": "Tapping (guitar technique)",
+    "146": "Strum",
+    "147": "Banjo",
+    "148": "Sitar",
+    "149": "Mandolin",
+    "150": "Zither",
+    "151": "Ukulele",
+    "152": "Keyboard (musical)",
+    "153": "Piano",
+    "154": "Electric piano",
+    "155": "Organ",
+    "156": "Electronic organ",
+    "157": "Hammond organ",
+    "158": "Synthesizer",
+    "159": "Sampler",
+    "160": "Harpsichord",
+    "161": "Percussion",
+    "162": "Drum kit",
+    "163": "Drum machine",
+    "164": "Drum",
+    "165": "Snare drum",
+    "166": "Rimshot",
+    "167": "Drum roll",
+    "168": "Bass drum",
+    "169": "Timpani",
+    "170": "Tabla",
+    "171": "Cymbal",
+    "172": "Hi-hat",
+    "173": "Wood block",
+    "174": "Tambourine",
+    "175": "Rattle (instrument)",
+    "176": "Maraca",
+    "177": "Gong",
+    "178": "Tubular bells",
+    "179": "Mallet percussion",
+    "180": "Marimba, xylophone",
+    "181": "Glockenspiel",
+    "182": "Vibraphone",
+    "183": "Steelpan",
+    "184": "Orchestra",
+    "185": "Brass instrument",
+    "186": "French horn",
+    "187": "Trumpet",
+    "188": "Trombone",
+    "189": "Bowed string instrument",
+    "190": "String section",
+    "191": "Violin, fiddle",
+    "192": "Pizzicato",
+    "193": "Cello",
+    "194": "Double bass",
+    "195": "Wind instrument, woodwind instrument",
+    "196": "Flute",
+    "197": "Saxophone",
+    "198": "Clarinet",
+    "199": "Harp",
+    "200": "Bell",
+    "201": "Church bell",
+    "202": "Jingle bell",
+    "203": "Bicycle bell",
+    "204": "Tuning fork",
+    "205": "Chime",
+    "206": "Wind chime",
+    "207": "Change ringing (campanology)",
+    "208": "Harmonica",
+    "209": "Accordion",
+    "210": "Bagpipes",
+    "211": "Didgeridoo",
+    "212": "Shofar",
+    "213": "Theremin",
+    "214": "Singing bowl",
+    "215": "Scratching (performance technique)",
+    "216": "Pop music",
+    "217": "Hip hop music",
+    "218": "Beatboxing",
+    "219": "Rock music",
+    "220": "Heavy metal",
+    "221": "Punk rock",
+    "222": "Grunge",
+    "223": "Progressive rock",
+    "224": "Rock and roll",
+    "225": "Psychedelic rock",
+    "226": "Rhythm and blues",
+    "227": "Soul music",
+    "228": "Reggae",
+    "229": "Country",
+    "230": "Swing music",
+    "231": "Bluegrass",
+    "232": "Funk",
+    "233": "Folk music",
+    "234": "Middle Eastern music",
+    "235": "Jazz",
+    "236": "Disco",
+    "237": "Classical music",
+    "238": "Opera",
+    "239": "Electronic music",
+    "240": "House music",
+    "241": "Techno",
+    "242": "Dubstep",
+    "243": "Drum and bass",
+    "244": "Electronica",
+    "245": "Electronic dance music",
+    "246": "Ambient music",
+    "247": "Trance music",
+    "248": "Music of Latin America",
+    "249": "Salsa music",
+    "250": "Flamenco",
+    "251": "Blues",
+    "252": "Music for children",
+    "253": "New-age music",
+    "254": "Vocal music",
+    "255": "A capella",
+    "256": "Music of Africa",
+    "257": "Afrobeat",
+    "258": "Christian music",
+    "259": "Gospel music",
+    "260": "Music of Asia",
+    "261": "Carnatic music",
+    "262": "Music of Bollywood",
+    "263": "Ska",
+    "264": "Traditional music",
+    "265": "Independent music",
+    "266": "Song",
+    "267": "Background music",
+    "268": "Theme music",
+    "269": "Jingle (music)",
+    "270": "Soundtrack music",
+    "271": "Lullaby",
+    "272": "Video game music",
+    "273": "Christmas music",
+    "274": "Dance music",
+    "275": "Wedding music",
+    "276": "Happy music",
+    "277": "Funny music",
+    "278": "Sad music",
+    "279": "Tender music",
+    "280": "Exciting music",
+    "281": "Angry music",
+    "282": "Scary music",
+    "283": "Wind",
+    "284": "Rustling leaves",
+    "285": "Wind noise (microphone)",
+    "286": "Thunderstorm",
+    "287": "Thunder",
+    "288": "Water",
+    "289": "Rain",
+    "290": "Raindrop",
+    "291": "Rain on surface",
+    "292": "Stream",
+    "293": "Waterfall",
+    "294": "Ocean",
+    "295": "Waves, surf",
+    "296": "Steam",
+    "297": "Gurgling",
+    "298": "Fire",
+    "299": "Crackle",
+    "300": "Vehicle",
+    "301": "Boat, Water vehicle",
+    "302": "Sailboat, sailing ship",
+    "303": "Rowboat, canoe, kayak",
+    "304": "Motorboat, speedboat",
+    "305": "Ship",
+    "306": "Motor vehicle (road)",
+    "307": "Car",
+    "308": "Vehicle horn, car horn, honking",
+    "309": "Toot",
+    "310": "Car alarm",
+    "311": "Power windows, electric windows",
+    "312": "Skidding",
+    "313": "Tire squeal",
+    "314": "Car passing by",
+    "315": "Race car, auto racing",
+    "316": "Truck",
+    "317": "Air brake",
+    "318": "Air horn, truck horn",
+    "319": "Reversing beeps",
+    "320": "Ice cream truck, ice cream van",
+    "321": "Bus",
+    "322": "Emergency vehicle",
+    "323": "Police car (siren)",
+    "324": "Ambulance (siren)",
+    "325": "Fire engine, fire truck (siren)",
+    "326": "Motorcycle",
+    "327": "Traffic noise, roadway noise",
+    "328": "Rail transport",
+    "329": "Train",
+    "330": "Train whistle",
+    "331": "Train horn",
+    "332": "Railroad car, train wagon",
+    "333": "Train wheels squealing",
+    "334": "Subway, metro, underground",
+    "335": "Aircraft",
+    "336": "Aircraft engine",
+    "337": "Jet engine",
+    "338": "Propeller, airscrew",
+    "339": "Helicopter",
+    "340": "Fixed-wing aircraft, airplane",
+    "341": "Bicycle",
+    "342": "Skateboard",
+    "343": "Engine",
+    "344": "Light engine (high frequency)",
+    "345": "Dental drill, dentist's drill",
+    "346": "Lawn mower",
+    "347": "Chainsaw",
+    "348": "Medium engine (mid frequency)",
+    "349": "Heavy engine (low frequency)",
+    "350": "Engine knocking",
+    "351": "Engine starting",
+    "352": "Idling",
+    "353": "Accelerating, revving, vroom",
+    "354": "Door",
+    "355": "Doorbell",
+    "356": "Ding-dong",
+    "357": "Sliding door",
+    "358": "Slam",
+    "359": "Knock",
+    "360": "Tap",
+    "361": "Squeak",
+    "362": "Cupboard open or close",
+    "363": "Drawer open or close",
+    "364": "Dishes, pots, and pans",
+    "365": "Cutlery, silverware",
+    "366": "Chopping (food)",
+    "367": "Frying (food)",
+    "368": "Microwave oven",
+    "369": "Blender",
+    "370": "Water tap, faucet",
+    "371": "Sink (filling or washing)",
+    "372": "Bathtub (filling or washing)",
+    "373": "Hair dryer",
+    "374": "Toilet flush",
+    "375": "Toothbrush",
+    "376": "Electric toothbrush",
+    "377": "Vacuum cleaner",
+    "378": "Zipper (clothing)",
+    "379": "Keys jangling",
+    "380": "Coin (dropping)",
+    "381": "Scissors",
+    "382": "Electric shaver, electric razor",
+    "383": "Shuffling cards",
+    "384": "Typing",
+    "385": "Typewriter",
+    "386": "Computer keyboard",
+    "387": "Writing",
+    "388": "Alarm",
+    "389": "Telephone",
+    "390": "Telephone bell ringing",
+    "391": "Ringtone",
+    "392": "Telephone dialing, DTMF",
+    "393": "Dial tone",
+    "394": "Busy signal",
+    "395": "Alarm clock",
+    "396": "Siren",
+    "397": "Civil defense siren",
+    "398": "Buzzer",
+    "399": "Smoke detector, smoke alarm",
+    "400": "Fire alarm",
+    "401": "Foghorn",
+    "402": "Whistle",
+    "403": "Steam whistle",
+    "404": "Mechanisms",
+    "405": "Ratchet, pawl",
+    "406": "Clock",
+    "407": "Tick",
+    "408": "Tick-tock",
+    "409": "Gears",
+    "410": "Pulleys",
+    "411": "Sewing machine",
+    "412": "Mechanical fan",
+    "413": "Air conditioning",
+    "414": "Cash register",
+    "415": "Printer",
+    "416": "Camera",
+    "417": "Single-lens reflex camera",
+    "418": "Tools",
+    "419": "Hammer",
+    "420": "Jackhammer",
+    "421": "Sawing",
+    "422": "Filing (rasp)",
+    "423": "Sanding",
+    "424": "Power tool",
+    "425": "Drill",
+    "426": "Explosion",
+    "427": "Gunshot, gunfire",
+    "428": "Machine gun",
+    "429": "Fusillade",
+    "430": "Artillery fire",
+    "431": "Cap gun",
+    "432": "Fireworks",
+    "433": "Firecracker",
+    "434": "Burst, pop",
+    "435": "Eruption",
+    "436": "Boom",
+    "437": "Wood",
+    "438": "Chop",
+    "439": "Splinter",
+    "440": "Crack",
+    "441": "Glass",
+    "442": "Chink, clink",
+    "443": "Shatter",
+    "444": "Liquid",
+    "445": "Splash, splatter",
+    "446": "Slosh",
+    "447": "Squish",
+    "448": "Drip",
+    "449": "Pour",
+    "450": "Trickle, dribble",
+    "451": "Gush",
+    "452": "Fill (with liquid)",
+    "453": "Spray",
+    "454": "Pump (liquid)",
+    "455": "Stir",
+    "456": "Boiling",
+    "457": "Sonar",
+    "458": "Arrow",
+    "459": "Whoosh, swoosh, swish",
+    "460": "Thump, thud",
+    "461": "Thunk",
+    "462": "Electronic tuner",
+    "463": "Effects unit",
+    "464": "Chorus effect",
+    "465": "Basketball bounce",
+    "466": "Bang",
+    "467": "Slap, smack",
+    "468": "Whack, thwack",
+    "469": "Smash, crash",
+    "470": "Breaking",
+    "471": "Bouncing",
+    "472": "Whip",
+    "473": "Flap",
+    "474": "Scratch",
+    "475": "Scrape",
+    "476": "Rub",
+    "477": "Roll",
+    "478": "Crushing",
+    "479": "Crumpling, crinkling",
+    "480": "Tearing",
+    "481": "Beep, bleep",
+    "482": "Ping",
+    "483": "Ding",
+    "484": "Clang",
+    "485": "Squeal",
+    "486": "Creak",
+    "487": "Rustle",
+    "488": "Whir",
+    "489": "Clatter",
+    "490": "Sizzle",
+    "491": "Clicking",
+    "492": "Clickety-clack",
+    "493": "Rumble",
+    "494": "Plop",
+    "495": "Jingle, tinkle",
+    "496": "Hum",
+    "497": "Zing",
+    "498": "Boing",
+    "499": "Crunch",
+    "500": "Silence",
+    "501": "Sine wave",
+    "502": "Harmonic",
+    "503": "Chirp tone",
+    "504": "Sound effect",
+    "505": "Pulse",
+    "506": "Inside, small room",
+    "507": "Inside, large room or hall",
+    "508": "Inside, public space",
+    "509": "Outside, urban or manmade",
+    "510": "Outside, rural or natural",
+    "511": "Reverberation",
+    "512": "Echo",
+    "513": "Noise",
+    "514": "Environmental noise",
+    "515": "Static",
+    "516": "Mains hum",
+    "517": "Distortion",
+    "518": "Sidetone",
+    "519": "Cacophony",
+    "520": "White noise",
+    "521": "Pink noise",
+    "522": "Throbbing",
+    "523": "Vibration",
+    "524": "Television",
+    "525": "Radio",
+    "526": "Field recording"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A capella": 255,
+    "Accelerating, revving, vroom": 353,
+    "Accordion": 209,
+    "Acoustic guitar": 143,
+    "Afrobeat": 257,
+    "Air brake": 317,
+    "Air conditioning": 413,
+    "Air horn, truck horn": 318,
+    "Aircraft": 335,
+    "Aircraft engine": 336,
+    "Alarm": 388,
+    "Alarm clock": 395,
+    "Ambient music": 246,
+    "Ambulance (siren)": 324,
+    "Angry music": 281,
+    "Animal": 72,
+    "Applause": 67,
+    "Arrow": 458,
+    "Artillery fire": 430,
+    "Babbling": 6,
+    "Baby cry, infant cry": 23,
+    "Baby laughter": 17,
+    "Background music": 267,
+    "Bagpipes": 210,
+    "Bang": 466,
+    "Banjo": 147,
+    "Bark": 75,
+    "Basketball bounce": 465,
+    "Bass drum": 168,
+    "Bass guitar": 142,
+    "Bathtub (filling or washing)": 372,
+    "Battle cry": 12,
+    "Beatboxing": 218,
+    "Bee, wasp, etc.": 131,
+    "Beep, bleep": 481,
+    "Bell": 200,
+    "Bellow": 9,
+    "Belly laugh": 20,
+    "Bicycle": 341,
+    "Bicycle bell": 203,
+    "Bird": 111,
+    "Bird flight, flapping wings": 121,
+    "Bird vocalization, bird call, bird song": 112,
+    "Biting": 55,
+    "Bleat": 96,
+    "Blender": 369,
+    "Bluegrass": 231,
+    "Blues": 251,
+    "Boat, Water vehicle": 301,
+    "Boiling": 456,
+    "Boing": 498,
+    "Boom": 436,
+    "Bouncing": 471,
+    "Bow-wow": 78,
+    "Bowed string instrument": 189,
+    "Brass instrument": 185,
+    "Breaking": 470,
+    "Breathing": 41,
+    "Burping, eructation": 58,
+    "Burst, pop": 434,
+    "Bus": 321,
+    "Busy signal": 394,
+    "Buzz": 130,
+    "Buzzer": 398,
+    "Cacophony": 519,
+    "Camera": 416,
+    "Canidae, dogs, wolves": 122,
+    "Cap gun": 431,
+    "Car": 307,
+    "Car alarm": 310,
+    "Car passing by": 314,
+    "Carnatic music": 261,
+    "Cash register": 414,
+    "Cat": 81,
+    "Caterwaul": 85,
+    "Cattle, bovinae": 90,
+    "Caw": 118,
+    "Cello": 193,
+    "Chainsaw": 347,
+    "Change ringing (campanology)": 207,
+    "Chant": 30,
+    "Chatter": 68,
+    "Cheering": 66,
+    "Chewing, mastication": 54,
+    "Chicken, rooster": 99,
+    "Child singing": 34,
+    "Child speech, kid speaking": 3,
+    "Children playing": 71,
+    "Children shouting": 13,
+    "Chime": 205,
+    "Chink, clink": 442,
+    "Chirp tone": 503,
+    "Chirp, tweet": 113,
+    "Choir": 28,
+    "Chop": 438,
+    "Chopping (food)": 366,
+    "Chorus effect": 464,
+    "Christian music": 258,
+    "Christmas music": 273,
+    "Chuckle, chortle": 21,
+    "Church bell": 201,
+    "Civil defense siren": 397,
+    "Clang": 484,
+    "Clapping": 63,
+    "Clarinet": 198,
+    "Classical music": 237,
+    "Clatter": 489,
+    "Clickety-clack": 492,
+    "Clicking": 491,
+    "Clip-clop": 88,
+    "Clock": 406,
+    "Cluck": 100,
+    "Coin (dropping)": 380,
+    "Computer keyboard": 386,
+    "Conversation": 4,
+    "Coo": 116,
+    "Cough": 47,
+    "Country": 229,
+    "Cowbell": 92,
+    "Crack": 440,
+    "Crackle": 299,
+    "Creak": 486,
+    "Cricket": 127,
+    "Croak": 133,
+    "Crow": 117,
+    "Crowd": 69,
+    "Crowing, cock-a-doodle-doo": 101,
+    "Crumpling, crinkling": 479,
+    "Crunch": 499,
+    "Crushing": 478,
+    "Crying, sobbing": 22,
+    "Cupboard open or close": 362,
+    "Cutlery, silverware": 365,
+    "Cymbal": 171,
+    "Dance music": 274,
+    "Dental drill, dentist's drill": 345,
+    "Dial tone": 393,
+    "Didgeridoo": 211,
+    "Ding": 483,
+    "Ding-dong": 356,
+    "Disco": 236,
+    "Dishes, pots, and pans": 364,
+    "Distortion": 517,
+    "Dog": 74,
+    "Domestic animals, pets": 73,
+    "Door": 354,
+    "Doorbell": 355,
+    "Double bass": 194,
+    "Drawer open or close": 363,
+    "Drill": 425,
+    "Drip": 448,
+    "Drum": 164,
+    "Drum and bass": 243,
+    "Drum kit": 162,
+    "Drum machine": 163,
+    "Drum roll": 167,
+    "Dubstep": 242,
+    "Duck": 104,
+    "Echo": 512,
+    "Effects unit": 463,
+    "Electric guitar": 141,
+    "Electric piano": 154,
+    "Electric shaver, electric razor": 382,
+    "Electric toothbrush": 376,
+    "Electronic dance music": 245,
+    "Electronic music": 239,
+    "Electronic organ": 156,
+    "Electronic tuner": 462,
+    "Electronica": 244,
+    "Emergency vehicle": 322,
+    "Engine": 343,
+    "Engine knocking": 350,
+    "Engine starting": 351,
+    "Environmental noise": 514,
+    "Eruption": 435,
+    "Exciting music": 280,
+    "Explosion": 426,
+    "Fart": 60,
+    "Female singing": 33,
+    "Female speech, woman speaking": 2,
+    "Field recording": 526,
+    "Filing (rasp)": 422,
+    "Fill (with liquid)": 452,
+    "Finger snapping": 62,
+    "Fire": 298,
+    "Fire alarm": 400,
+    "Fire engine, fire truck (siren)": 325,
+    "Firecracker": 433,
+    "Fireworks": 432,
+    "Fixed-wing aircraft, airplane": 340,
+    "Flamenco": 250,
+    "Flap": 473,
+    "Flute": 196,
+    "Fly, housefly": 129,
+    "Foghorn": 401,
+    "Folk music": 233,
+    "Fowl": 98,
+    "French horn": 186,
+    "Frog": 132,
+    "Frying (food)": 367,
+    "Funk": 232,
+    "Funny music": 277,
+    "Fusillade": 429,
+    "Gargling": 56,
+    "Gasp": 44,
+    "Gears": 409,
+    "Giggle": 18,
+    "Glass": 441,
+    "Glockenspiel": 181,
+    "Goat": 95,
+    "Gobble": 103,
+    "Gong": 177,
+    "Goose": 106,
+    "Gospel music": 259,
+    "Groan": 38,
+    "Growling": 79,
+    "Grunge": 222,
+    "Grunt": 39,
+    "Guitar": 140,
+    "Gunshot, gunfire": 427,
+    "Gurgling": 297,
+    "Gush": 451,
+    "Hair dryer": 373,
+    "Hammer": 419,
+    "Hammond organ": 157,
+    "Hands": 61,
+    "Happy music": 276,
+    "Harmonic": 502,
+    "Harmonica": 208,
+    "Harp": 199,
+    "Harpsichord": 160,
+    "Heart murmur": 65,
+    "Heart sounds, heartbeat": 64,
+    "Heavy engine (low frequency)": 349,
+    "Heavy metal": 220,
+    "Helicopter": 339,
+    "Hi-hat": 172,
+    "Hiccup": 59,
+    "Hip hop music": 217,
+    "Hiss": 84,
+    "Honk": 107,
+    "Hoot": 120,
+    "Horse": 87,
+    "House music": 240,
+    "Howl": 77,
+    "Hubbub, speech noise, speech babble": 70,
+    "Hum": 496,
+    "Humming": 37,
+    "Ice cream truck, ice cream van": 320,
+    "Idling": 352,
+    "Independent music": 265,
+    "Insect": 126,
+    "Inside, large room or hall": 507,
+    "Inside, public space": 508,
+    "Inside, small room": 506,
+    "Jackhammer": 420,
+    "Jazz": 235,
+    "Jet engine": 337,
+    "Jingle (music)": 269,
+    "Jingle bell": 202,
+    "Jingle, tinkle": 495,
+    "Keyboard (musical)": 152,
+    "Keys jangling": 379,
+    "Knock": 359,
+    "Laughter": 16,
+    "Lawn mower": 346,
+    "Light engine (high frequency)": 344,
+    "Liquid": 444,
+    "Livestock, farm animals, working animals": 86,
+    "Lullaby": 271,
+    "Machine gun": 428,
+    "Mains hum": 516,
+    "Male singing": 32,
+    "Male speech, man speaking": 1,
+    "Mallet percussion": 179,
+    "Mandolin": 149,
+    "Mantra": 31,
+    "Maraca": 176,
+    "Marimba, xylophone": 180,
+    "Mechanical fan": 412,
+    "Mechanisms": 404,
+    "Medium engine (mid frequency)": 348,
+    "Meow": 83,
+    "Microwave oven": 368,
+    "Middle Eastern music": 234,
+    "Moo": 91,
+    "Mosquito": 128,
+    "Motor vehicle (road)": 306,
+    "Motorboat, speedboat": 304,
+    "Motorcycle": 326,
+    "Mouse": 124,
+    "Music": 137,
+    "Music for children": 252,
+    "Music of Africa": 256,
+    "Music of Asia": 260,
+    "Music of Bollywood": 262,
+    "Music of Latin America": 248,
+    "Musical instrument": 138,
+    "Narration, monologue": 5,
+    "Neigh, whinny": 89,
+    "New-age music": 253,
+    "Noise": 513,
+    "Ocean": 294,
+    "Oink": 94,
+    "Opera": 238,
+    "Orchestra": 184,
+    "Organ": 155,
+    "Outside, rural or natural": 510,
+    "Outside, urban or manmade": 509,
+    "Owl": 119,
+    "Pant": 45,
+    "Patter": 125,
+    "Percussion": 161,
+    "Piano": 153,
+    "Pig": 93,
+    "Pigeon, dove": 115,
+    "Ping": 482,
+    "Pink noise": 521,
+    "Pizzicato": 192,
+    "Plop": 494,
+    "Plucked string instrument": 139,
+    "Police car (siren)": 323,
+    "Pop music": 216,
+    "Pour": 449,
+    "Power tool": 424,
+    "Power windows, electric windows": 311,
+    "Printer": 415,
+    "Progressive rock": 223,
+    "Propeller, airscrew": 338,
+    "Psychedelic rock": 225,
+    "Pulleys": 410,
+    "Pulse": 505,
+    "Pump (liquid)": 454,
+    "Punk rock": 221,
+    "Purr": 82,
+    "Quack": 105,
+    "Race car, auto racing": 315,
+    "Radio": 525,
+    "Rail transport": 328,
+    "Railroad car, train wagon": 332,
+    "Rain": 289,
+    "Rain on surface": 291,
+    "Raindrop": 290,
+    "Rapping": 36,
+    "Ratchet, pawl": 405,
+    "Rattle": 135,
+    "Rattle (instrument)": 175,
+    "Reggae": 228,
+    "Reverberation": 511,
+    "Reversing beeps": 319,
+    "Rhythm and blues": 226,
+    "Rimshot": 166,
+    "Ringtone": 391,
+    "Roar": 110,
+    "Roaring cats (lions, tigers)": 109,
+    "Rock and roll": 224,
+    "Rock music": 219,
+    "Rodents, rats, mice": 123,
+    "Roll": 477,
+    "Rowboat, canoe, kayak": 303,
+    "Rub": 476,
+    "Rumble": 493,
+    "Run": 51,
+    "Rustle": 487,
+    "Rustling leaves": 284,
+    "Sad music": 278,
+    "Sailboat, sailing ship": 302,
+    "Salsa music": 249,
+    "Sampler": 159,
+    "Sanding": 423,
+    "Sawing": 421,
+    "Saxophone": 197,
+    "Scary music": 282,
+    "Scissors": 381,
+    "Scrape": 475,
+    "Scratch": 474,
+    "Scratching (performance technique)": 215,
+    "Screaming": 14,
+    "Sewing machine": 411,
+    "Shatter": 443,
+    "Sheep": 97,
+    "Ship": 305,
+    "Shofar": 212,
+    "Shout": 8,
+    "Shuffle": 52,
+    "Shuffling cards": 383,
+    "Sidetone": 518,
+    "Sigh": 26,
+    "Silence": 500,
+    "Sine wave": 501,
+    "Singing": 27,
+    "Singing bowl": 214,
+    "Single-lens reflex camera": 417,
+    "Sink (filling or washing)": 371,
+    "Siren": 396,
+    "Sitar": 148,
+    "Sizzle": 490,
+    "Ska": 263,
+    "Skateboard": 342,
+    "Skidding": 312,
+    "Slam": 358,
+    "Slap, smack": 467,
+    "Sliding door": 357,
+    "Slosh": 446,
+    "Smash, crash": 469,
+    "Smoke detector, smoke alarm": 399,
+    "Snake": 134,
+    "Snare drum": 165,
+    "Sneeze": 49,
+    "Snicker": 19,
+    "Sniff": 50,
+    "Snoring": 43,
+    "Snort": 46,
+    "Sonar": 457,
+    "Song": 266,
+    "Soul music": 227,
+    "Sound effect": 504,
+    "Soundtrack music": 270,
+    "Speech": 0,
+    "Speech synthesizer": 7,
+    "Splash, splatter": 445,
+    "Splinter": 439,
+    "Spray": 453,
+    "Squawk": 114,
+    "Squeak": 361,
+    "Squeal": 485,
+    "Squish": 447,
+    "Static": 515,
+    "Steam": 296,
+    "Steam whistle": 403,
+    "Steel guitar, slide guitar": 144,
+    "Steelpan": 183,
+    "Stir": 455,
+    "Stomach rumble": 57,
+    "Stream": 292,
+    "String section": 190,
+    "Strum": 146,
+    "Subway, metro, underground": 334,
+    "Swing music": 230,
+    "Synthesizer": 158,
+    "Synthetic singing": 35,
+    "Tabla": 170,
+    "Tambourine": 174,
+    "Tap": 360,
+    "Tapping (guitar technique)": 145,
+    "Tearing": 480,
+    "Techno": 241,
+    "Telephone": 389,
+    "Telephone bell ringing": 390,
+    "Telephone dialing, DTMF": 392,
+    "Television": 524,
+    "Tender music": 279,
+    "Theme music": 268,
+    "Theremin": 213,
+    "Throat clearing": 48,
+    "Throbbing": 522,
+    "Thump, thud": 460,
+    "Thunder": 287,
+    "Thunderstorm": 286,
+    "Thunk": 461,
+    "Tick": 407,
+    "Tick-tock": 408,
+    "Timpani": 169,
+    "Tire squeal": 313,
+    "Toilet flush": 374,
+    "Tools": 418,
+    "Toot": 309,
+    "Toothbrush": 375,
+    "Traditional music": 264,
+    "Traffic noise, roadway noise": 327,
+    "Train": 329,
+    "Train horn": 331,
+    "Train wheels squealing": 333,
+    "Train whistle": 330,
+    "Trance music": 247,
+    "Trickle, dribble": 450,
+    "Trombone": 188,
+    "Truck": 316,
+    "Trumpet": 187,
+    "Tubular bells": 178,
+    "Tuning fork": 204,
+    "Turkey": 102,
+    "Typewriter": 385,
+    "Typing": 384,
+    "Ukulele": 151,
+    "Vacuum cleaner": 377,
+    "Vehicle": 300,
+    "Vehicle horn, car horn, honking": 308,
+    "Vibraphone": 182,
+    "Vibration": 523,
+    "Video game music": 272,
+    "Violin, fiddle": 191,
+    "Vocal music": 254,
+    "Wail, moan": 25,
+    "Walk, footsteps": 53,
+    "Water": 288,
+    "Water tap, faucet": 370,
+    "Waterfall": 293,
+    "Waves, surf": 295,
+    "Wedding music": 275,
+    "Whack, thwack": 468,
+    "Whale vocalization": 136,
+    "Wheeze": 42,
+    "Whimper": 24,
+    "Whimper (dog)": 80,
+    "Whip": 472,
+    "Whir": 488,
+    "Whispering": 15,
+    "Whistle": 402,
+    "Whistling": 40,
+    "White noise": 520,
+    "Whoop": 10,
+    "Whoosh, swoosh, swish": 459,
+    "Wild animals": 108,
+    "Wind": 283,
+    "Wind chime": 206,
+    "Wind instrument, woodwind instrument": 195,
+    "Wind noise (microphone)": 285,
+    "Wood": 437,
+    "Wood block": 173,
+    "Writing": 387,
+    "Yell": 11,
+    "Yip": 76,
+    "Yodeling": 29,
+    "Zing": 497,
+    "Zipper (clothing)": 378,
+    "Zither": 150
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

output/augmented_esc50/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864e1cf06d6b17acdb458122ab0d8a6345dd203266bf6ee94fe91dec36b3d6ba
+size 346404948

output/augmented_esc50/test_results.json

@@ -0,0 +1,8 @@
+{
+    "test_accuracy": 0.9835,
+    "test_loss": 0.07399206608533859,
+    "test_model_preparation_time": 0.1745,
+    "test_runtime": 110.5501,
+    "test_samples_per_second": 18.091,
+    "test_steps_per_second": 2.261
+}

output/augmented_esc50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68089c73da00e5426fbe1b7586cd81a39a15f1747aca4941237d2ea1255dd76
+size 5240

output/checkpoint-800/config.json

@@ -0,0 +1,1082 @@
+{
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Speech",
+    "1": "Male speech, man speaking",
+    "2": "Female speech, woman speaking",
+    "3": "Child speech, kid speaking",
+    "4": "Conversation",
+    "5": "Narration, monologue",
+    "6": "Babbling",
+    "7": "Speech synthesizer",
+    "8": "Shout",
+    "9": "Bellow",
+    "10": "Whoop",
+    "11": "Yell",
+    "12": "Battle cry",
+    "13": "Children shouting",
+    "14": "Screaming",
+    "15": "Whispering",
+    "16": "Laughter",
+    "17": "Baby laughter",
+    "18": "Giggle",
+    "19": "Snicker",
+    "20": "Belly laugh",
+    "21": "Chuckle, chortle",
+    "22": "Crying, sobbing",
+    "23": "Baby cry, infant cry",
+    "24": "Whimper",
+    "25": "Wail, moan",
+    "26": "Sigh",
+    "27": "Singing",
+    "28": "Choir",
+    "29": "Yodeling",
+    "30": "Chant",
+    "31": "Mantra",
+    "32": "Male singing",
+    "33": "Female singing",
+    "34": "Child singing",
+    "35": "Synthetic singing",
+    "36": "Rapping",
+    "37": "Humming",
+    "38": "Groan",
+    "39": "Grunt",
+    "40": "Whistling",
+    "41": "Breathing",
+    "42": "Wheeze",
+    "43": "Snoring",
+    "44": "Gasp",
+    "45": "Pant",
+    "46": "Snort",
+    "47": "Cough",
+    "48": "Throat clearing",
+    "49": "Sneeze",
+    "50": "Sniff",
+    "51": "Run",
+    "52": "Shuffle",
+    "53": "Walk, footsteps",
+    "54": "Chewing, mastication",
+    "55": "Biting",
+    "56": "Gargling",
+    "57": "Stomach rumble",
+    "58": "Burping, eructation",
+    "59": "Hiccup",
+    "60": "Fart",
+    "61": "Hands",
+    "62": "Finger snapping",
+    "63": "Clapping",
+    "64": "Heart sounds, heartbeat",
+    "65": "Heart murmur",
+    "66": "Cheering",
+    "67": "Applause",
+    "68": "Chatter",
+    "69": "Crowd",
+    "70": "Hubbub, speech noise, speech babble",
+    "71": "Children playing",
+    "72": "Animal",
+    "73": "Domestic animals, pets",
+    "74": "Dog",
+    "75": "Bark",
+    "76": "Yip",
+    "77": "Howl",
+    "78": "Bow-wow",
+    "79": "Growling",
+    "80": "Whimper (dog)",
+    "81": "Cat",
+    "82": "Purr",
+    "83": "Meow",
+    "84": "Hiss",
+    "85": "Caterwaul",
+    "86": "Livestock, farm animals, working animals",
+    "87": "Horse",
+    "88": "Clip-clop",
+    "89": "Neigh, whinny",
+    "90": "Cattle, bovinae",
+    "91": "Moo",
+    "92": "Cowbell",
+    "93": "Pig",
+    "94": "Oink",
+    "95": "Goat",
+    "96": "Bleat",
+    "97": "Sheep",
+    "98": "Fowl",
+    "99": "Chicken, rooster",
+    "100": "Cluck",
+    "101": "Crowing, cock-a-doodle-doo",
+    "102": "Turkey",
+    "103": "Gobble",
+    "104": "Duck",
+    "105": "Quack",
+    "106": "Goose",
+    "107": "Honk",
+    "108": "Wild animals",
+    "109": "Roaring cats (lions, tigers)",
+    "110": "Roar",
+    "111": "Bird",
+    "112": "Bird vocalization, bird call, bird song",
+    "113": "Chirp, tweet",
+    "114": "Squawk",
+    "115": "Pigeon, dove",
+    "116": "Coo",
+    "117": "Crow",
+    "118": "Caw",
+    "119": "Owl",
+    "120": "Hoot",
+    "121": "Bird flight, flapping wings",
+    "122": "Canidae, dogs, wolves",
+    "123": "Rodents, rats, mice",
+    "124": "Mouse",
+    "125": "Patter",
+    "126": "Insect",
+    "127": "Cricket",
+    "128": "Mosquito",
+    "129": "Fly, housefly",
+    "130": "Buzz",
+    "131": "Bee, wasp, etc.",
+    "132": "Frog",
+    "133": "Croak",
+    "134": "Snake",
+    "135": "Rattle",
+    "136": "Whale vocalization",
+    "137": "Music",
+    "138": "Musical instrument",
+    "139": "Plucked string instrument",
+    "140": "Guitar",
+    "141": "Electric guitar",
+    "142": "Bass guitar",
+    "143": "Acoustic guitar",
+    "144": "Steel guitar, slide guitar",
+    "145": "Tapping (guitar technique)",
+    "146": "Strum",
+    "147": "Banjo",
+    "148": "Sitar",
+    "149": "Mandolin",
+    "150": "Zither",
+    "151": "Ukulele",
+    "152": "Keyboard (musical)",
+    "153": "Piano",
+    "154": "Electric piano",
+    "155": "Organ",
+    "156": "Electronic organ",
+    "157": "Hammond organ",
+    "158": "Synthesizer",
+    "159": "Sampler",
+    "160": "Harpsichord",
+    "161": "Percussion",
+    "162": "Drum kit",
+    "163": "Drum machine",
+    "164": "Drum",
+    "165": "Snare drum",
+    "166": "Rimshot",
+    "167": "Drum roll",
+    "168": "Bass drum",
+    "169": "Timpani",
+    "170": "Tabla",
+    "171": "Cymbal",
+    "172": "Hi-hat",
+    "173": "Wood block",
+    "174": "Tambourine",
+    "175": "Rattle (instrument)",
+    "176": "Maraca",
+    "177": "Gong",
+    "178": "Tubular bells",
+    "179": "Mallet percussion",
+    "180": "Marimba, xylophone",
+    "181": "Glockenspiel",
+    "182": "Vibraphone",
+    "183": "Steelpan",
+    "184": "Orchestra",
+    "185": "Brass instrument",
+    "186": "French horn",
+    "187": "Trumpet",
+    "188": "Trombone",
+    "189": "Bowed string instrument",
+    "190": "String section",
+    "191": "Violin, fiddle",
+    "192": "Pizzicato",
+    "193": "Cello",
+    "194": "Double bass",
+    "195": "Wind instrument, woodwind instrument",
+    "196": "Flute",
+    "197": "Saxophone",
+    "198": "Clarinet",
+    "199": "Harp",
+    "200": "Bell",
+    "201": "Church bell",
+    "202": "Jingle bell",
+    "203": "Bicycle bell",
+    "204": "Tuning fork",
+    "205": "Chime",
+    "206": "Wind chime",
+    "207": "Change ringing (campanology)",
+    "208": "Harmonica",
+    "209": "Accordion",
+    "210": "Bagpipes",
+    "211": "Didgeridoo",
+    "212": "Shofar",
+    "213": "Theremin",
+    "214": "Singing bowl",
+    "215": "Scratching (performance technique)",
+    "216": "Pop music",
+    "217": "Hip hop music",
+    "218": "Beatboxing",
+    "219": "Rock music",
+    "220": "Heavy metal",
+    "221": "Punk rock",
+    "222": "Grunge",
+    "223": "Progressive rock",
+    "224": "Rock and roll",
+    "225": "Psychedelic rock",
+    "226": "Rhythm and blues",
+    "227": "Soul music",
+    "228": "Reggae",
+    "229": "Country",
+    "230": "Swing music",
+    "231": "Bluegrass",
+    "232": "Funk",
+    "233": "Folk music",
+    "234": "Middle Eastern music",
+    "235": "Jazz",
+    "236": "Disco",
+    "237": "Classical music",
+    "238": "Opera",
+    "239": "Electronic music",
+    "240": "House music",
+    "241": "Techno",
+    "242": "Dubstep",
+    "243": "Drum and bass",
+    "244": "Electronica",
+    "245": "Electronic dance music",
+    "246": "Ambient music",
+    "247": "Trance music",
+    "248": "Music of Latin America",
+    "249": "Salsa music",
+    "250": "Flamenco",
+    "251": "Blues",
+    "252": "Music for children",
+    "253": "New-age music",
+    "254": "Vocal music",
+    "255": "A capella",
+    "256": "Music of Africa",
+    "257": "Afrobeat",
+    "258": "Christian music",
+    "259": "Gospel music",
+    "260": "Music of Asia",
+    "261": "Carnatic music",
+    "262": "Music of Bollywood",
+    "263": "Ska",
+    "264": "Traditional music",
+    "265": "Independent music",
+    "266": "Song",
+    "267": "Background music",
+    "268": "Theme music",
+    "269": "Jingle (music)",
+    "270": "Soundtrack music",
+    "271": "Lullaby",
+    "272": "Video game music",
+    "273": "Christmas music",
+    "274": "Dance music",
+    "275": "Wedding music",
+    "276": "Happy music",
+    "277": "Funny music",
+    "278": "Sad music",
+    "279": "Tender music",
+    "280": "Exciting music",
+    "281": "Angry music",
+    "282": "Scary music",
+    "283": "Wind",
+    "284": "Rustling leaves",
+    "285": "Wind noise (microphone)",
+    "286": "Thunderstorm",
+    "287": "Thunder",
+    "288": "Water",
+    "289": "Rain",
+    "290": "Raindrop",
+    "291": "Rain on surface",
+    "292": "Stream",
+    "293": "Waterfall",
+    "294": "Ocean",
+    "295": "Waves, surf",
+    "296": "Steam",
+    "297": "Gurgling",
+    "298": "Fire",
+    "299": "Crackle",
+    "300": "Vehicle",
+    "301": "Boat, Water vehicle",
+    "302": "Sailboat, sailing ship",
+    "303": "Rowboat, canoe, kayak",
+    "304": "Motorboat, speedboat",
+    "305": "Ship",
+    "306": "Motor vehicle (road)",
+    "307": "Car",
+    "308": "Vehicle horn, car horn, honking",
+    "309": "Toot",
+    "310": "Car alarm",
+    "311": "Power windows, electric windows",
+    "312": "Skidding",
+    "313": "Tire squeal",
+    "314": "Car passing by",
+    "315": "Race car, auto racing",
+    "316": "Truck",
+    "317": "Air brake",
+    "318": "Air horn, truck horn",
+    "319": "Reversing beeps",
+    "320": "Ice cream truck, ice cream van",
+    "321": "Bus",
+    "322": "Emergency vehicle",
+    "323": "Police car (siren)",
+    "324": "Ambulance (siren)",
+    "325": "Fire engine, fire truck (siren)",
+    "326": "Motorcycle",
+    "327": "Traffic noise, roadway noise",
+    "328": "Rail transport",
+    "329": "Train",
+    "330": "Train whistle",
+    "331": "Train horn",
+    "332": "Railroad car, train wagon",
+    "333": "Train wheels squealing",
+    "334": "Subway, metro, underground",
+    "335": "Aircraft",
+    "336": "Aircraft engine",
+    "337": "Jet engine",
+    "338": "Propeller, airscrew",
+    "339": "Helicopter",
+    "340": "Fixed-wing aircraft, airplane",
+    "341": "Bicycle",
+    "342": "Skateboard",
+    "343": "Engine",
+    "344": "Light engine (high frequency)",
+    "345": "Dental drill, dentist's drill",
+    "346": "Lawn mower",
+    "347": "Chainsaw",
+    "348": "Medium engine (mid frequency)",
+    "349": "Heavy engine (low frequency)",
+    "350": "Engine knocking",
+    "351": "Engine starting",
+    "352": "Idling",
+    "353": "Accelerating, revving, vroom",
+    "354": "Door",
+    "355": "Doorbell",
+    "356": "Ding-dong",
+    "357": "Sliding door",
+    "358": "Slam",
+    "359": "Knock",
+    "360": "Tap",
+    "361": "Squeak",
+    "362": "Cupboard open or close",
+    "363": "Drawer open or close",
+    "364": "Dishes, pots, and pans",
+    "365": "Cutlery, silverware",
+    "366": "Chopping (food)",
+    "367": "Frying (food)",
+    "368": "Microwave oven",
+    "369": "Blender",
+    "370": "Water tap, faucet",
+    "371": "Sink (filling or washing)",
+    "372": "Bathtub (filling or washing)",
+    "373": "Hair dryer",
+    "374": "Toilet flush",
+    "375": "Toothbrush",
+    "376": "Electric toothbrush",
+    "377": "Vacuum cleaner",
+    "378": "Zipper (clothing)",
+    "379": "Keys jangling",
+    "380": "Coin (dropping)",
+    "381": "Scissors",
+    "382": "Electric shaver, electric razor",
+    "383": "Shuffling cards",
+    "384": "Typing",
+    "385": "Typewriter",
+    "386": "Computer keyboard",
+    "387": "Writing",
+    "388": "Alarm",
+    "389": "Telephone",
+    "390": "Telephone bell ringing",
+    "391": "Ringtone",
+    "392": "Telephone dialing, DTMF",
+    "393": "Dial tone",
+    "394": "Busy signal",
+    "395": "Alarm clock",
+    "396": "Siren",
+    "397": "Civil defense siren",
+    "398": "Buzzer",
+    "399": "Smoke detector, smoke alarm",
+    "400": "Fire alarm",
+    "401": "Foghorn",
+    "402": "Whistle",
+    "403": "Steam whistle",
+    "404": "Mechanisms",
+    "405": "Ratchet, pawl",
+    "406": "Clock",
+    "407": "Tick",
+    "408": "Tick-tock",
+    "409": "Gears",
+    "410": "Pulleys",
+    "411": "Sewing machine",
+    "412": "Mechanical fan",
+    "413": "Air conditioning",
+    "414": "Cash register",
+    "415": "Printer",
+    "416": "Camera",
+    "417": "Single-lens reflex camera",
+    "418": "Tools",
+    "419": "Hammer",
+    "420": "Jackhammer",
+    "421": "Sawing",
+    "422": "Filing (rasp)",
+    "423": "Sanding",
+    "424": "Power tool",
+    "425": "Drill",
+    "426": "Explosion",
+    "427": "Gunshot, gunfire",
+    "428": "Machine gun",
+    "429": "Fusillade",
+    "430": "Artillery fire",
+    "431": "Cap gun",
+    "432": "Fireworks",
+    "433": "Firecracker",
+    "434": "Burst, pop",
+    "435": "Eruption",
+    "436": "Boom",
+    "437": "Wood",
+    "438": "Chop",
+    "439": "Splinter",
+    "440": "Crack",
+    "441": "Glass",
+    "442": "Chink, clink",
+    "443": "Shatter",
+    "444": "Liquid",
+    "445": "Splash, splatter",
+    "446": "Slosh",
+    "447": "Squish",
+    "448": "Drip",
+    "449": "Pour",
+    "450": "Trickle, dribble",
+    "451": "Gush",
+    "452": "Fill (with liquid)",
+    "453": "Spray",
+    "454": "Pump (liquid)",
+    "455": "Stir",
+    "456": "Boiling",
+    "457": "Sonar",
+    "458": "Arrow",
+    "459": "Whoosh, swoosh, swish",
+    "460": "Thump, thud",
+    "461": "Thunk",
+    "462": "Electronic tuner",
+    "463": "Effects unit",
+    "464": "Chorus effect",
+    "465": "Basketball bounce",
+    "466": "Bang",
+    "467": "Slap, smack",
+    "468": "Whack, thwack",
+    "469": "Smash, crash",
+    "470": "Breaking",
+    "471": "Bouncing",
+    "472": "Whip",
+    "473": "Flap",
+    "474": "Scratch",
+    "475": "Scrape",
+    "476": "Rub",
+    "477": "Roll",
+    "478": "Crushing",
+    "479": "Crumpling, crinkling",
+    "480": "Tearing",
+    "481": "Beep, bleep",
+    "482": "Ping",
+    "483": "Ding",
+    "484": "Clang",
+    "485": "Squeal",
+    "486": "Creak",
+    "487": "Rustle",
+    "488": "Whir",
+    "489": "Clatter",
+    "490": "Sizzle",
+    "491": "Clicking",
+    "492": "Clickety-clack",
+    "493": "Rumble",
+    "494": "Plop",
+    "495": "Jingle, tinkle",
+    "496": "Hum",
+    "497": "Zing",
+    "498": "Boing",
+    "499": "Crunch",
+    "500": "Silence",
+    "501": "Sine wave",
+    "502": "Harmonic",
+    "503": "Chirp tone",
+    "504": "Sound effect",
+    "505": "Pulse",
+    "506": "Inside, small room",
+    "507": "Inside, large room or hall",
+    "508": "Inside, public space",
+    "509": "Outside, urban or manmade",
+    "510": "Outside, rural or natural",
+    "511": "Reverberation",
+    "512": "Echo",
+    "513": "Noise",
+    "514": "Environmental noise",
+    "515": "Static",
+    "516": "Mains hum",
+    "517": "Distortion",
+    "518": "Sidetone",
+    "519": "Cacophony",
+    "520": "White noise",
+    "521": "Pink noise",
+    "522": "Throbbing",
+    "523": "Vibration",
+    "524": "Television",
+    "525": "Radio",
+    "526": "Field recording"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A capella": 255,
+    "Accelerating, revving, vroom": 353,
+    "Accordion": 209,
+    "Acoustic guitar": 143,
+    "Afrobeat": 257,
+    "Air brake": 317,
+    "Air conditioning": 413,
+    "Air horn, truck horn": 318,
+    "Aircraft": 335,
+    "Aircraft engine": 336,
+    "Alarm": 388,
+    "Alarm clock": 395,
+    "Ambient music": 246,
+    "Ambulance (siren)": 324,
+    "Angry music": 281,
+    "Animal": 72,
+    "Applause": 67,
+    "Arrow": 458,
+    "Artillery fire": 430,
+    "Babbling": 6,
+    "Baby cry, infant cry": 23,
+    "Baby laughter": 17,
+    "Background music": 267,
+    "Bagpipes": 210,
+    "Bang": 466,
+    "Banjo": 147,
+    "Bark": 75,
+    "Basketball bounce": 465,
+    "Bass drum": 168,
+    "Bass guitar": 142,
+    "Bathtub (filling or washing)": 372,
+    "Battle cry": 12,
+    "Beatboxing": 218,
+    "Bee, wasp, etc.": 131,
+    "Beep, bleep": 481,
+    "Bell": 200,
+    "Bellow": 9,
+    "Belly laugh": 20,
+    "Bicycle": 341,
+    "Bicycle bell": 203,
+    "Bird": 111,
+    "Bird flight, flapping wings": 121,
+    "Bird vocalization, bird call, bird song": 112,
+    "Biting": 55,
+    "Bleat": 96,
+    "Blender": 369,
+    "Bluegrass": 231,
+    "Blues": 251,
+    "Boat, Water vehicle": 301,
+    "Boiling": 456,
+    "Boing": 498,
+    "Boom": 436,
+    "Bouncing": 471,
+    "Bow-wow": 78,
+    "Bowed string instrument": 189,
+    "Brass instrument": 185,
+    "Breaking": 470,
+    "Breathing": 41,
+    "Burping, eructation": 58,
+    "Burst, pop": 434,
+    "Bus": 321,
+    "Busy signal": 394,
+    "Buzz": 130,
+    "Buzzer": 398,
+    "Cacophony": 519,
+    "Camera": 416,
+    "Canidae, dogs, wolves": 122,
+    "Cap gun": 431,
+    "Car": 307,
+    "Car alarm": 310,
+    "Car passing by": 314,
+    "Carnatic music": 261,
+    "Cash register": 414,
+    "Cat": 81,
+    "Caterwaul": 85,
+    "Cattle, bovinae": 90,
+    "Caw": 118,
+    "Cello": 193,
+    "Chainsaw": 347,
+    "Change ringing (campanology)": 207,
+    "Chant": 30,
+    "Chatter": 68,
+    "Cheering": 66,
+    "Chewing, mastication": 54,
+    "Chicken, rooster": 99,
+    "Child singing": 34,
+    "Child speech, kid speaking": 3,
+    "Children playing": 71,
+    "Children shouting": 13,
+    "Chime": 205,
+    "Chink, clink": 442,
+    "Chirp tone": 503,
+    "Chirp, tweet": 113,
+    "Choir": 28,
+    "Chop": 438,
+    "Chopping (food)": 366,
+    "Chorus effect": 464,
+    "Christian music": 258,
+    "Christmas music": 273,
+    "Chuckle, chortle": 21,
+    "Church bell": 201,
+    "Civil defense siren": 397,
+    "Clang": 484,
+    "Clapping": 63,
+    "Clarinet": 198,
+    "Classical music": 237,
+    "Clatter": 489,
+    "Clickety-clack": 492,
+    "Clicking": 491,
+    "Clip-clop": 88,
+    "Clock": 406,
+    "Cluck": 100,
+    "Coin (dropping)": 380,
+    "Computer keyboard": 386,
+    "Conversation": 4,
+    "Coo": 116,
+    "Cough": 47,
+    "Country": 229,
+    "Cowbell": 92,
+    "Crack": 440,
+    "Crackle": 299,
+    "Creak": 486,
+    "Cricket": 127,
+    "Croak": 133,
+    "Crow": 117,
+    "Crowd": 69,
+    "Crowing, cock-a-doodle-doo": 101,
+    "Crumpling, crinkling": 479,
+    "Crunch": 499,
+    "Crushing": 478,
+    "Crying, sobbing": 22,
+    "Cupboard open or close": 362,
+    "Cutlery, silverware": 365,
+    "Cymbal": 171,
+    "Dance music": 274,
+    "Dental drill, dentist's drill": 345,
+    "Dial tone": 393,
+    "Didgeridoo": 211,
+    "Ding": 483,
+    "Ding-dong": 356,
+    "Disco": 236,
+    "Dishes, pots, and pans": 364,
+    "Distortion": 517,
+    "Dog": 74,
+    "Domestic animals, pets": 73,
+    "Door": 354,
+    "Doorbell": 355,
+    "Double bass": 194,
+    "Drawer open or close": 363,
+    "Drill": 425,
+    "Drip": 448,
+    "Drum": 164,
+    "Drum and bass": 243,
+    "Drum kit": 162,
+    "Drum machine": 163,
+    "Drum roll": 167,
+    "Dubstep": 242,
+    "Duck": 104,
+    "Echo": 512,
+    "Effects unit": 463,
+    "Electric guitar": 141,
+    "Electric piano": 154,
+    "Electric shaver, electric razor": 382,
+    "Electric toothbrush": 376,
+    "Electronic dance music": 245,
+    "Electronic music": 239,
+    "Electronic organ": 156,
+    "Electronic tuner": 462,
+    "Electronica": 244,
+    "Emergency vehicle": 322,
+    "Engine": 343,
+    "Engine knocking": 350,
+    "Engine starting": 351,
+    "Environmental noise": 514,
+    "Eruption": 435,
+    "Exciting music": 280,
+    "Explosion": 426,
+    "Fart": 60,
+    "Female singing": 33,
+    "Female speech, woman speaking": 2,
+    "Field recording": 526,
+    "Filing (rasp)": 422,
+    "Fill (with liquid)": 452,
+    "Finger snapping": 62,
+    "Fire": 298,
+    "Fire alarm": 400,
+    "Fire engine, fire truck (siren)": 325,
+    "Firecracker": 433,
+    "Fireworks": 432,
+    "Fixed-wing aircraft, airplane": 340,
+    "Flamenco": 250,
+    "Flap": 473,
+    "Flute": 196,
+    "Fly, housefly": 129,
+    "Foghorn": 401,
+    "Folk music": 233,
+    "Fowl": 98,
+    "French horn": 186,
+    "Frog": 132,
+    "Frying (food)": 367,
+    "Funk": 232,
+    "Funny music": 277,
+    "Fusillade": 429,
+    "Gargling": 56,
+    "Gasp": 44,
+    "Gears": 409,
+    "Giggle": 18,
+    "Glass": 441,
+    "Glockenspiel": 181,
+    "Goat": 95,
+    "Gobble": 103,
+    "Gong": 177,
+    "Goose": 106,
+    "Gospel music": 259,
+    "Groan": 38,
+    "Growling": 79,
+    "Grunge": 222,
+    "Grunt": 39,
+    "Guitar": 140,
+    "Gunshot, gunfire": 427,
+    "Gurgling": 297,
+    "Gush": 451,
+    "Hair dryer": 373,
+    "Hammer": 419,
+    "Hammond organ": 157,
+    "Hands": 61,
+    "Happy music": 276,
+    "Harmonic": 502,
+    "Harmonica": 208,
+    "Harp": 199,
+    "Harpsichord": 160,
+    "Heart murmur": 65,
+    "Heart sounds, heartbeat": 64,
+    "Heavy engine (low frequency)": 349,
+    "Heavy metal": 220,
+    "Helicopter": 339,
+    "Hi-hat": 172,
+    "Hiccup": 59,
+    "Hip hop music": 217,
+    "Hiss": 84,
+    "Honk": 107,
+    "Hoot": 120,
+    "Horse": 87,
+    "House music": 240,
+    "Howl": 77,
+    "Hubbub, speech noise, speech babble": 70,
+    "Hum": 496,
+    "Humming": 37,
+    "Ice cream truck, ice cream van": 320,
+    "Idling": 352,
+    "Independent music": 265,
+    "Insect": 126,
+    "Inside, large room or hall": 507,
+    "Inside, public space": 508,
+    "Inside, small room": 506,
+    "Jackhammer": 420,
+    "Jazz": 235,
+    "Jet engine": 337,
+    "Jingle (music)": 269,
+    "Jingle bell": 202,
+    "Jingle, tinkle": 495,
+    "Keyboard (musical)": 152,
+    "Keys jangling": 379,
+    "Knock": 359,
+    "Laughter": 16,
+    "Lawn mower": 346,
+    "Light engine (high frequency)": 344,
+    "Liquid": 444,
+    "Livestock, farm animals, working animals": 86,
+    "Lullaby": 271,
+    "Machine gun": 428,
+    "Mains hum": 516,
+    "Male singing": 32,
+    "Male speech, man speaking": 1,
+    "Mallet percussion": 179,
+    "Mandolin": 149,
+    "Mantra": 31,
+    "Maraca": 176,
+    "Marimba, xylophone": 180,
+    "Mechanical fan": 412,
+    "Mechanisms": 404,
+    "Medium engine (mid frequency)": 348,
+    "Meow": 83,
+    "Microwave oven": 368,
+    "Middle Eastern music": 234,
+    "Moo": 91,
+    "Mosquito": 128,
+    "Motor vehicle (road)": 306,
+    "Motorboat, speedboat": 304,
+    "Motorcycle": 326,
+    "Mouse": 124,
+    "Music": 137,
+    "Music for children": 252,
+    "Music of Africa": 256,
+    "Music of Asia": 260,
+    "Music of Bollywood": 262,
+    "Music of Latin America": 248,
+    "Musical instrument": 138,
+    "Narration, monologue": 5,
+    "Neigh, whinny": 89,
+    "New-age music": 253,
+    "Noise": 513,
+    "Ocean": 294,
+    "Oink": 94,
+    "Opera": 238,
+    "Orchestra": 184,
+    "Organ": 155,
+    "Outside, rural or natural": 510,
+    "Outside, urban or manmade": 509,
+    "Owl": 119,
+    "Pant": 45,
+    "Patter": 125,
+    "Percussion": 161,
+    "Piano": 153,
+    "Pig": 93,
+    "Pigeon, dove": 115,
+    "Ping": 482,
+    "Pink noise": 521,
+    "Pizzicato": 192,
+    "Plop": 494,
+    "Plucked string instrument": 139,
+    "Police car (siren)": 323,
+    "Pop music": 216,
+    "Pour": 449,
+    "Power tool": 424,
+    "Power windows, electric windows": 311,
+    "Printer": 415,
+    "Progressive rock": 223,
+    "Propeller, airscrew": 338,
+    "Psychedelic rock": 225,
+    "Pulleys": 410,
+    "Pulse": 505,
+    "Pump (liquid)": 454,
+    "Punk rock": 221,
+    "Purr": 82,
+    "Quack": 105,
+    "Race car, auto racing": 315,
+    "Radio": 525,
+    "Rail transport": 328,
+    "Railroad car, train wagon": 332,
+    "Rain": 289,
+    "Rain on surface": 291,
+    "Raindrop": 290,
+    "Rapping": 36,
+    "Ratchet, pawl": 405,
+    "Rattle": 135,
+    "Rattle (instrument)": 175,
+    "Reggae": 228,
+    "Reverberation": 511,
+    "Reversing beeps": 319,
+    "Rhythm and blues": 226,
+    "Rimshot": 166,
+    "Ringtone": 391,
+    "Roar": 110,
+    "Roaring cats (lions, tigers)": 109,
+    "Rock and roll": 224,
+    "Rock music": 219,
+    "Rodents, rats, mice": 123,
+    "Roll": 477,
+    "Rowboat, canoe, kayak": 303,
+    "Rub": 476,
+    "Rumble": 493,
+    "Run": 51,
+    "Rustle": 487,
+    "Rustling leaves": 284,
+    "Sad music": 278,
+    "Sailboat, sailing ship": 302,
+    "Salsa music": 249,
+    "Sampler": 159,
+    "Sanding": 423,
+    "Sawing": 421,
+    "Saxophone": 197,
+    "Scary music": 282,
+    "Scissors": 381,
+    "Scrape": 475,
+    "Scratch": 474,
+    "Scratching (performance technique)": 215,
+    "Screaming": 14,
+    "Sewing machine": 411,
+    "Shatter": 443,
+    "Sheep": 97,
+    "Ship": 305,
+    "Shofar": 212,
+    "Shout": 8,
+    "Shuffle": 52,
+    "Shuffling cards": 383,
+    "Sidetone": 518,
+    "Sigh": 26,
+    "Silence": 500,
+    "Sine wave": 501,
+    "Singing": 27,
+    "Singing bowl": 214,
+    "Single-lens reflex camera": 417,
+    "Sink (filling or washing)": 371,
+    "Siren": 396,
+    "Sitar": 148,
+    "Sizzle": 490,
+    "Ska": 263,
+    "Skateboard": 342,
+    "Skidding": 312,
+    "Slam": 358,
+    "Slap, smack": 467,
+    "Sliding door": 357,
+    "Slosh": 446,
+    "Smash, crash": 469,
+    "Smoke detector, smoke alarm": 399,
+    "Snake": 134,
+    "Snare drum": 165,
+    "Sneeze": 49,
+    "Snicker": 19,
+    "Sniff": 50,
+    "Snoring": 43,
+    "Snort": 46,
+    "Sonar": 457,
+    "Song": 266,
+    "Soul music": 227,
+    "Sound effect": 504,
+    "Soundtrack music": 270,
+    "Speech": 0,
+    "Speech synthesizer": 7,
+    "Splash, splatter": 445,
+    "Splinter": 439,
+    "Spray": 453,
+    "Squawk": 114,
+    "Squeak": 361,
+    "Squeal": 485,
+    "Squish": 447,
+    "Static": 515,
+    "Steam": 296,
+    "Steam whistle": 403,
+    "Steel guitar, slide guitar": 144,
+    "Steelpan": 183,
+    "Stir": 455,
+    "Stomach rumble": 57,
+    "Stream": 292,
+    "String section": 190,
+    "Strum": 146,
+    "Subway, metro, underground": 334,
+    "Swing music": 230,
+    "Synthesizer": 158,
+    "Synthetic singing": 35,
+    "Tabla": 170,
+    "Tambourine": 174,
+    "Tap": 360,
+    "Tapping (guitar technique)": 145,
+    "Tearing": 480,
+    "Techno": 241,
+    "Telephone": 389,
+    "Telephone bell ringing": 390,
+    "Telephone dialing, DTMF": 392,
+    "Television": 524,
+    "Tender music": 279,
+    "Theme music": 268,
+    "Theremin": 213,
+    "Throat clearing": 48,
+    "Throbbing": 522,
+    "Thump, thud": 460,
+    "Thunder": 287,
+    "Thunderstorm": 286,
+    "Thunk": 461,
+    "Tick": 407,
+    "Tick-tock": 408,
+    "Timpani": 169,
+    "Tire squeal": 313,
+    "Toilet flush": 374,
+    "Tools": 418,
+    "Toot": 309,
+    "Toothbrush": 375,
+    "Traditional music": 264,
+    "Traffic noise, roadway noise": 327,
+    "Train": 329,
+    "Train horn": 331,
+    "Train wheels squealing": 333,
+    "Train whistle": 330,
+    "Trance music": 247,
+    "Trickle, dribble": 450,
+    "Trombone": 188,
+    "Truck": 316,
+    "Trumpet": 187,
+    "Tubular bells": 178,
+    "Tuning fork": 204,
+    "Turkey": 102,
+    "Typewriter": 385,
+    "Typing": 384,
+    "Ukulele": 151,
+    "Vacuum cleaner": 377,
+    "Vehicle": 300,
+    "Vehicle horn, car horn, honking": 308,
+    "Vibraphone": 182,
+    "Vibration": 523,
+    "Video game music": 272,
+    "Violin, fiddle": 191,
+    "Vocal music": 254,
+    "Wail, moan": 25,
+    "Walk, footsteps": 53,
+    "Water": 288,
+    "Water tap, faucet": 370,
+    "Waterfall": 293,
+    "Waves, surf": 295,
+    "Wedding music": 275,
+    "Whack, thwack": 468,
+    "Whale vocalization": 136,
+    "Wheeze": 42,
+    "Whimper": 24,
+    "Whimper (dog)": 80,
+    "Whip": 472,
+    "Whir": 488,
+    "Whispering": 15,
+    "Whistle": 402,
+    "Whistling": 40,
+    "White noise": 520,
+    "Whoop": 10,
+    "Whoosh, swoosh, swish": 459,
+    "Wild animals": 108,
+    "Wind": 283,
+    "Wind chime": 206,
+    "Wind instrument, woodwind instrument": 195,
+    "Wind noise (microphone)": 285,
+    "Wood": 437,
+    "Wood block": 173,
+    "Writing": 387,
+    "Yell": 11,
+    "Yip": 76,
+    "Yodeling": 29,
+    "Zing": 497,
+    "Zipper (clothing)": 378,
+    "Zither": 150
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

output/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864e1cf06d6b17acdb458122ab0d8a6345dd203266bf6ee94fe91dec36b3d6ba
+size 346404948

output/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c031f7af877b2e517b21c625ad6bef7bfa16d61b53359c634348bea663268cce
+size 692922234

output/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44a53784733ae7dcb55555ed75e1fea306bd7427001380dc0f3854a19687855
+size 14244

output/checkpoint-800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72827407676228bfcecbcd7d9941c8dd2c10e15de40f1068670c9723cfb158f4
+size 988

output/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a70640ef0bda14850c1234bc04d2da04e34340ea1dcc8cfed6e8df07c937b5b
+size 1064

output/checkpoint-800/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.9125,
+  "best_model_checkpoint": "./output\\checkpoint-800",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 21.84564971923828,
+      "learning_rate": 9.52e-06,
+      "loss": 4.9576,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 19.016281127929688,
+      "learning_rate": 9.020000000000002e-06,
+      "loss": 2.5629,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.67,
+      "eval_loss": 1.8187137842178345,
+      "eval_runtime": 16.628,
+      "eval_samples_per_second": 24.056,
+      "eval_steps_per_second": 1.503,
+      "step": 100
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 25.35007667541504,
+      "learning_rate": 8.52e-06,
+      "loss": 1.059,
+      "step": 150
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 24.2031307220459,
+      "learning_rate": 8.020000000000001e-06,
+      "loss": 0.5219,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.87,
+      "eval_loss": 0.631913423538208,
+      "eval_runtime": 16.5993,
+      "eval_samples_per_second": 24.097,
+      "eval_steps_per_second": 1.506,
+      "step": 200
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 15.069940567016602,
+      "learning_rate": 7.520000000000001e-06,
+      "loss": 0.188,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 11.744084358215332,
+      "learning_rate": 7.0200000000000006e-06,
+      "loss": 0.1404,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.89,
+      "eval_loss": 0.512397050857544,
+      "eval_runtime": 16.7187,
+      "eval_samples_per_second": 23.925,
+      "eval_steps_per_second": 1.495,
+      "step": 300
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 3.0763916969299316,
+      "learning_rate": 6.520000000000001e-06,
+      "loss": 0.0512,
+      "step": 350
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.471693754196167,
+      "learning_rate": 6.02e-06,
+      "loss": 0.0324,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8975,
+      "eval_loss": 0.42938971519470215,
+      "eval_runtime": 16.9732,
+      "eval_samples_per_second": 23.567,
+      "eval_steps_per_second": 1.473,
+      "step": 400
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.6510960459709167,
+      "learning_rate": 5.5200000000000005e-06,
+      "loss": 0.0148,
+      "step": 450
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2619748115539551,
+      "learning_rate": 5.02e-06,
+      "loss": 0.0075,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.905,
+      "eval_loss": 0.4057503640651703,
+      "eval_runtime": 17.0908,
+      "eval_samples_per_second": 23.404,
+      "eval_steps_per_second": 1.463,
+      "step": 500
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.11626938730478287,
+      "learning_rate": 4.520000000000001e-06,
+      "loss": 0.0045,
+      "step": 550
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.18584977090358734,
+      "learning_rate": 4.0200000000000005e-06,
+      "loss": 0.0036,
+      "step": 600
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9075,
+      "eval_loss": 0.40661507844924927,
+      "eval_runtime": 17.3315,
+      "eval_samples_per_second": 23.079,
+      "eval_steps_per_second": 1.442,
+      "step": 600
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.11915897578001022,
+      "learning_rate": 3.52e-06,
+      "loss": 0.0027,
+      "step": 650
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.1160835325717926,
+      "learning_rate": 3.0200000000000003e-06,
+      "loss": 0.0023,
+      "step": 700
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.91,
+      "eval_loss": 0.40690818428993225,
+      "eval_runtime": 17.0897,
+      "eval_samples_per_second": 23.406,
+      "eval_steps_per_second": 1.463,
+      "step": 700
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.057445961982011795,
+      "learning_rate": 2.52e-06,
+      "loss": 0.002,
+      "step": 750
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.07348606735467911,
+      "learning_rate": 2.02e-06,
+      "loss": 0.002,
+      "step": 800
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9125,
+      "eval_loss": 0.404008150100708,
+      "eval_runtime": 17.1756,
+      "eval_samples_per_second": 23.289,
+      "eval_steps_per_second": 1.456,
+      "step": 800
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.716843795611648e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

output/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68089c73da00e5426fbe1b7586cd81a39a15f1747aca4941237d2ea1255dd76
+size 5240

test.py

@@ -0,0 +1,23 @@
+from transformers import TrainingArguments
+
+from functions import prepare_datasets, make_trainer, get_model
+
+
+def main():
+    output_dir = "./output/augmented_esc50"
+
+    test_ds, _ = prepare_datasets(apply_augmentation=False)
+
+    # Use same model & args as training
+    model = get_model("MIT/ast-finetuned-audioset-10-10-0.4593")
+
+    training_args = TrainingArguments(output_dir=output_dir)
+    trainer = make_trainer(model, None, None, training_args)
+
+    trainer.model = model.from_pretrained(output_dir)
+
+    pred_output = trainer.predict(test_ds)
+    trainer.save_metrics("test", pred_output.metrics)
+
+if __name__ == "__main__":
+    main()

train.py

@@ -0,0 +1,77 @@
+import os
+import argparse
+from transformers import TrainingArguments
+from functions import (
+    prepare_datasets,
+    get_model,
+    make_trainer,
+    save_results
+)
+from dataset import get_latest_checkpoint, split_by_fold
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--model_name', default="MIT/ast-finetuned-audioset-10-10-0.4593")
+    parser.add_argument('--output_dir', default="./output")
+    parser.add_argument('--num_experiments', type=int, default=10)
+    parser.add_argument('--csv_path', default="./output/logs_results_augmented_esc50.csv")
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+    os.makedirs(args.output_dir, exist_ok=True)
+
+    # Prepare data (augmented)
+    dataset, _ = prepare_datasets(apply_augmentation=True)
+
+    # Initialize model and Trainer args
+    model = get_model(args.model_name)
+    training_args = TrainingArguments(
+        output_dir=args.output_dir,
+        logging_dir=os.path.join(args.output_dir, "logs"),
+        logging_steps=50,
+        do_train=True,
+        do_eval=True,
+        eval_strategy='epoch',
+        per_device_train_batch_size=16,
+        per_device_eval_batch_size=16,
+        num_train_epochs=10,
+        learning_rate=1e-5,
+        weight_decay=0.01,
+        save_total_limit=1,
+        save_strategy='epoch',
+        fp16=True,
+        load_best_model_at_end=True,
+        metric_for_best_model="accuracy",
+    )
+
+    results = []
+    trainer = None
+    # Multiple experiments
+    for i in range(args.num_experiments):
+        print(f"=== Experiment {i+1} ===")
+        train_ds, eval_ds = split_by_fold(dataset)
+        trainer = make_trainer(model, train_ds, eval_ds, training_args)
+
+        ckpt = get_latest_checkpoint(args.output_dir)
+        if ckpt:
+            print(f"Resuming from {ckpt}")
+            train_out = trainer.train(resume_from_checkpoint=ckpt)
+        else:
+            train_out = trainer.train()
+
+        eval_out = trainer.evaluate()
+        stats = {f"train_{k}": v for k,v in train_out.metrics.items()}
+        stats.update({f"eval_{k}": v for k,v in eval_out.items()})
+        stats['experiment_id'] = i+1
+        results.append(stats)
+
+    # Save final model (best checkpoint)
+    trainer.save_model(os.path.join(args.output_dir, "augmented_esc50"))
+    save_results(results, args.csv_path)
+
+
+if __name__ == "__main__":
+    main()