End of training

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+datasets:
+- audiofolder
+metrics:
+- accuracy
+model-index:
+- name: my_birdcall_model
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: audiofolder
+      type: audiofolder
+      config: rb
+      split: train
+      args: rb
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.09525756336876533
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# my_birdcall_model
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.1044
+- Accuracy: 0.0953
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 4.925         | 1.0   | 153  | 4.9054          | 0.0194   |
+| 4.6287        | 2.0   | 306  | 4.5973          | 0.0356   |
+| 4.4783        | 3.0   | 459  | 4.4897          | 0.0478   |
+| 4.3947        | 4.0   | 612  | 4.4000          | 0.0576   |
+| 4.3246        | 5.0   | 765  | 4.3330          | 0.0681   |
+| 4.2475        | 6.0   | 918  | 4.2791          | 0.0769   |
+| 4.1713        | 7.0   | 1071 | 4.2455          | 0.0809   |
+| 4.1255        | 8.0   | 1224 | 4.2108          | 0.0765   |
+| 4.0992        | 9.0   | 1377 | 4.1849          | 0.0820   |
+| 4.0128        | 10.0  | 1530 | 4.1478          | 0.0914   |
+| 3.9299        | 11.0  | 1683 | 4.1618          | 0.0865   |
+| 3.9218        | 12.0  | 1836 | 4.1216          | 0.0916   |
+| 3.8447        | 13.0  | 1989 | 4.1305          | 0.0942   |
+| 3.8873        | 14.0  | 2142 | 4.1120          | 0.0942   |
+| 3.8107        | 15.0  | 2295 | 4.1044          | 0.0953   |
+
+
+### Framework versions
+
+- Transformers 4.38.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,486 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "asbfly",
+    "1": "ashdro1",
+    "10": "bcnher",
+    "100": "labcro1",
+    "101": "laudov1",
+    "102": "lblwar1",
+    "103": "lesyel1",
+    "104": "lewduc1",
+    "105": "lirplo",
+    "106": "litegr",
+    "107": "litgre1",
+    "108": "litspi1",
+    "109": "litswi1",
+    "11": "bkcbul1",
+    "110": "lobsun2",
+    "111": "maghor2",
+    "112": "malpar1",
+    "113": "maltro1",
+    "114": "malwoo1",
+    "115": "marsan",
+    "116": "mawthr1",
+    "117": "moipig1",
+    "118": "nilfly2",
+    "119": "niwpig1",
+    "12": "bkrfla1",
+    "120": "nutman",
+    "121": "orihob2",
+    "122": "oripip1",
+    "123": "pabflo1",
+    "124": "paisto1",
+    "125": "piebus1",
+    "126": "piekin1",
+    "127": "placuc3",
+    "128": "plaflo1",
+    "129": "plapri1",
+    "13": "bkskit1",
+    "130": "plhpar1",
+    "131": "pomgrp2",
+    "132": "purher1",
+    "133": "pursun3",
+    "134": "pursun4",
+    "135": "purswa3",
+    "136": "putbab1",
+    "137": "redspu1",
+    "138": "rerswa1",
+    "139": "revbul",
+    "14": "bkwsti",
+    "140": "rewbul",
+    "141": "rewlap1",
+    "142": "rocpig",
+    "143": "rorpar",
+    "144": "rossta2",
+    "145": "rufbab3",
+    "146": "ruftre2",
+    "147": "rufwoo2",
+    "148": "rutfly6",
+    "149": "sbeowl1",
+    "15": "bladro1",
+    "150": "scamin3",
+    "151": "shikra1",
+    "152": "smamin1",
+    "153": "sohmyn1",
+    "154": "spepic1",
+    "155": "spodov",
+    "156": "spoowl1",
+    "157": "sqtbul1",
+    "158": "stbkin1",
+    "159": "sttwoo1",
+    "16": "blaeag1",
+    "160": "thbwar1",
+    "161": "tibfly3",
+    "162": "tilwar1",
+    "163": "vefnut1",
+    "164": "vehpar1",
+    "165": "wbbfly1",
+    "166": "wemhar1",
+    "167": "whbbul2",
+    "168": "whbsho3",
+    "169": "whbtre1",
+    "17": "blakit1",
+    "170": "whbwag1",
+    "171": "whbwat1",
+    "172": "whbwoo2",
+    "173": "whcbar1",
+    "174": "whiter2",
+    "175": "whrmun",
+    "176": "whtkin2",
+    "177": "woosan",
+    "178": "wynlau1",
+    "179": "yebbab1",
+    "18": "blhori1",
+    "180": "yebbul3",
+    "181": "zitcis1",
+    "19": "blnmon1",
+    "2": "ashpri1",
+    "20": "blrwar1",
+    "21": "bncwoo3",
+    "22": "brakit1",
+    "23": "brasta1",
+    "24": "brcful1",
+    "25": "brfowl1",
+    "26": "brnhao1",
+    "27": "brnshr",
+    "28": "brodro1",
+    "29": "brwjac1",
+    "3": "ashwoo2",
+    "30": "brwowl1",
+    "31": "btbeat1",
+    "32": "bwfshr1",
+    "33": "categr",
+    "34": "chbeat1",
+    "35": "cohcuc1",
+    "36": "comfla1",
+    "37": "comgre",
+    "38": "comior1",
+    "39": "comkin1",
+    "4": "asikoe2",
+    "40": "commoo3",
+    "41": "commyn",
+    "42": "compea",
+    "43": "comros",
+    "44": "comsan",
+    "45": "comtai1",
+    "46": "copbar1",
+    "47": "crbsun2",
+    "48": "cregos1",
+    "49": "crfbar1",
+    "5": "asiope1",
+    "50": "crseag1",
+    "51": "dafbab1",
+    "52": "darter2",
+    "53": "eaywag1",
+    "54": "emedov2",
+    "55": "eucdov",
+    "56": "eurbla2",
+    "57": "eurcoo",
+    "58": "forwag1",
+    "59": "gargan",
+    "6": "aspfly1",
+    "60": "gloibi",
+    "61": "goflea1",
+    "62": "graher1",
+    "63": "grbeat1",
+    "64": "grecou1",
+    "65": "greegr",
+    "66": "grefla1",
+    "67": "grehor1",
+    "68": "grejun2",
+    "69": "grenig1",
+    "7": "aspswi1",
+    "70": "grewar3",
+    "71": "grnsan",
+    "72": "grnwar1",
+    "73": "grtdro1",
+    "74": "gryfra",
+    "75": "grynig2",
+    "76": "grywag",
+    "77": "gybpri1",
+    "78": "gyhcaf1",
+    "79": "heswoo1",
+    "8": "barfly1",
+    "80": "hoopoe",
+    "81": "houcro1",
+    "82": "houspa",
+    "83": "inbrob1",
+    "84": "indpit1",
+    "85": "indrob1",
+    "86": "indrol2",
+    "87": "indtit1",
+    "88": "ingori1",
+    "89": "inpher1",
+    "9": "barswa",
+    "90": "insbab1",
+    "91": "insowl1",
+    "92": "integr",
+    "93": "isbduc1",
+    "94": "jerbus2",
+    "95": "junbab2",
+    "96": "junmyn1",
+    "97": "junowl1",
+    "98": "kenplo1",
+    "99": "kerlau2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "asbfly": "0",
+    "ashdro1": "1",
+    "ashpri1": "2",
+    "ashwoo2": "3",
+    "asikoe2": "4",
+    "asiope1": "5",
+    "aspfly1": "6",
+    "aspswi1": "7",
+    "barfly1": "8",
+    "barswa": "9",
+    "bcnher": "10",
+    "bkcbul1": "11",
+    "bkrfla1": "12",
+    "bkskit1": "13",
+    "bkwsti": "14",
+    "bladro1": "15",
+    "blaeag1": "16",
+    "blakit1": "17",
+    "blhori1": "18",
+    "blnmon1": "19",
+    "blrwar1": "20",
+    "bncwoo3": "21",
+    "brakit1": "22",
+    "brasta1": "23",
+    "brcful1": "24",
+    "brfowl1": "25",
+    "brnhao1": "26",
+    "brnshr": "27",
+    "brodro1": "28",
+    "brwjac1": "29",
+    "brwowl1": "30",
+    "btbeat1": "31",
+    "bwfshr1": "32",
+    "categr": "33",
+    "chbeat1": "34",
+    "cohcuc1": "35",
+    "comfla1": "36",
+    "comgre": "37",
+    "comior1": "38",
+    "comkin1": "39",
+    "commoo3": "40",
+    "commyn": "41",
+    "compea": "42",
+    "comros": "43",
+    "comsan": "44",
+    "comtai1": "45",
+    "copbar1": "46",
+    "crbsun2": "47",
+    "cregos1": "48",
+    "crfbar1": "49",
+    "crseag1": "50",
+    "dafbab1": "51",
+    "darter2": "52",
+    "eaywag1": "53",
+    "emedov2": "54",
+    "eucdov": "55",
+    "eurbla2": "56",
+    "eurcoo": "57",
+    "forwag1": "58",
+    "gargan": "59",
+    "gloibi": "60",
+    "goflea1": "61",
+    "graher1": "62",
+    "grbeat1": "63",
+    "grecou1": "64",
+    "greegr": "65",
+    "grefla1": "66",
+    "grehor1": "67",
+    "grejun2": "68",
+    "grenig1": "69",
+    "grewar3": "70",
+    "grnsan": "71",
+    "grnwar1": "72",
+    "grtdro1": "73",
+    "gryfra": "74",
+    "grynig2": "75",
+    "grywag": "76",
+    "gybpri1": "77",
+    "gyhcaf1": "78",
+    "heswoo1": "79",
+    "hoopoe": "80",
+    "houcro1": "81",
+    "houspa": "82",
+    "inbrob1": "83",
+    "indpit1": "84",
+    "indrob1": "85",
+    "indrol2": "86",
+    "indtit1": "87",
+    "ingori1": "88",
+    "inpher1": "89",
+    "insbab1": "90",
+    "insowl1": "91",
+    "integr": "92",
+    "isbduc1": "93",
+    "jerbus2": "94",
+    "junbab2": "95",
+    "junmyn1": "96",
+    "junowl1": "97",
+    "kenplo1": "98",
+    "kerlau2": "99",
+    "labcro1": "100",
+    "laudov1": "101",
+    "lblwar1": "102",
+    "lesyel1": "103",
+    "lewduc1": "104",
+    "lirplo": "105",
+    "litegr": "106",
+    "litgre1": "107",
+    "litspi1": "108",
+    "litswi1": "109",
+    "lobsun2": "110",
+    "maghor2": "111",
+    "malpar1": "112",
+    "maltro1": "113",
+    "malwoo1": "114",
+    "marsan": "115",
+    "mawthr1": "116",
+    "moipig1": "117",
+    "nilfly2": "118",
+    "niwpig1": "119",
+    "nutman": "120",
+    "orihob2": "121",
+    "oripip1": "122",
+    "pabflo1": "123",
+    "paisto1": "124",
+    "piebus1": "125",
+    "piekin1": "126",
+    "placuc3": "127",
+    "plaflo1": "128",
+    "plapri1": "129",
+    "plhpar1": "130",
+    "pomgrp2": "131",
+    "purher1": "132",
+    "pursun3": "133",
+    "pursun4": "134",
+    "purswa3": "135",
+    "putbab1": "136",
+    "redspu1": "137",
+    "rerswa1": "138",
+    "revbul": "139",
+    "rewbul": "140",
+    "rewlap1": "141",
+    "rocpig": "142",
+    "rorpar": "143",
+    "rossta2": "144",
+    "rufbab3": "145",
+    "ruftre2": "146",
+    "rufwoo2": "147",
+    "rutfly6": "148",
+    "sbeowl1": "149",
+    "scamin3": "150",
+    "shikra1": "151",
+    "smamin1": "152",
+    "sohmyn1": "153",
+    "spepic1": "154",
+    "spodov": "155",
+    "spoowl1": "156",
+    "sqtbul1": "157",
+    "stbkin1": "158",
+    "sttwoo1": "159",
+    "thbwar1": "160",
+    "tibfly3": "161",
+    "tilwar1": "162",
+    "vefnut1": "163",
+    "vehpar1": "164",
+    "wbbfly1": "165",
+    "wemhar1": "166",
+    "whbbul2": "167",
+    "whbsho3": "168",
+    "whbtre1": "169",
+    "whbwag1": "170",
+    "whbwat1": "171",
+    "whbwoo2": "172",
+    "whcbar1": "173",
+    "whiter2": "174",
+    "whrmun": "175",
+    "whtkin2": "176",
+    "woosan": "177",
+    "wynlau1": "178",
+    "yebbab1": "179",
+    "yebbul3": "180",
+    "zitcis1": "181"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e7500f996f6d8c2aa7639c7a2bd5e092c8ce5ea5471292eecdbd3d70d37358
+size 378487416

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237ee0c8f2f50e257f29184049998068bc2773ac3d8adf0b202c5d77afeba4f1
+size 4920