Add model

README.md

@@ -0,0 +1,34 @@
+---
+license: apache-2.0
+metrics:
+- accuracy
+- roc_auc
+---
+[Music genre](https://en.wikipedia.org/wiki/Music_genre) classification is a fundamental and versatile application in many various domains. Some possible use cases for music genre classification include:
+
+- music recommendation systems;
+- content organization and discovery;
+- radio broadcasting and programming;
+- music licensing and copyright management;
+- music analysis and research;
+- content tagging and metadata enrichment;
+- audio identification and copyright protection;
+- music production and creativity;
+- healthcare and therapy;
+- entertainment and gaming.
+
+The model is trained based on publicly available dataset of labeled music data — [GTZAN Dataset](https://www.kaggle.com/datasets/andradaolteanu/gtzan-dataset-music-genre-classification) — that contains 1000 sample 30-second audio files evenly split among 10 genres:
+
+- blues;
+- classical;
+- country;
+- disco;
+- hip-hop;
+- jazz;
+- metal;
+- pop;
+- reggae;
+- rock.
+
+The final code is available as a [Kaggle notebook](https://www.kaggle.com/code/dima806/music-genre-classification-wav2vec2-base-960h).
+See also [my Medium article](https://medium.com/data-and-beyond/building-a-free-advanced-music-genre-classification-pipeline-using-machine-learning-654b0de7cc3e)  for more details.

config.json

@@ -0,0 +1,133 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "disco",
+    "1": "metal",
+    "2": "reggae",
+    "3": "blues",
+    "4": "rock",
+    "5": "classical",
+    "6": "jazz",
+    "7": "hiphop",
+    "8": "country",
+    "9": "pop"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "model_type": "wav2vec2",
+  "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": "4.28.1",
+  "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 sha256:71198c7a652fede1d3c64b5e2bcf0b5a0511ec564f49bd6abbe47a20d254caa0
+size 378310544

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36e8d7542c20a973b2295cd2aa4d3aa469720aaf2ef1bece1f80720e51d7122
+size 378356755

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a7b8a791db16485108725a93c291741023d2fe95e5a842e3860116709d6e65
+size 3567