Upload 5 files

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: bsd-3-clause
 tags:
 - generated_from_trainer
 datasets:
@@ -7,19 +7,32 @@ datasets:
 metrics:
 - accuracy
 model-index:
-- name: distilhubert-finetuned-gtzan-v3
-  results: []
+- name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: GTZAN
+      type: marsyas/gtzan
+      config: all
+      split: train
+      args: all
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9
 ---
 
 <!-- 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. -->
 
-# distilhubert-finetuned-gtzan-v3
+# ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
 
-This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
+This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5752
-- Accuracy: 0.83
+- Loss: 0.4717
+- Accuracy: 0.9
 
 ## Model description
 
@@ -39,38 +52,45 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
 - 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
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9108        | 1.0   | 113  | 1.9472          | 0.43     |
-| 1.3286        | 2.0   | 226  | 1.4173          | 0.65     |
-| 1.032         | 3.0   | 339  | 0.9815          | 0.67     |
-| 0.726         | 4.0   | 452  | 0.7403          | 0.79     |
-| 0.4621        | 5.0   | 565  | 0.6390          | 0.8      |
-| 0.3439        | 6.0   | 678  | 0.5248          | 0.85     |
-| 0.1592        | 7.0   | 791  | 0.4861          | 0.86     |
-| 0.1283        | 8.0   | 904  | 0.4995          | 0.87     |
-| 0.1191        | 9.0   | 1017 | 0.4804          | 0.87     |
-| 0.0236        | 10.0  | 1130 | 0.6737          | 0.8      |
-| 0.0146        | 11.0  | 1243 | 0.6211          | 0.81     |
-| 0.0105        | 12.0  | 1356 | 0.5806          | 0.86     |
-| 0.008         | 13.0  | 1469 | 0.5645          | 0.84     |
-| 0.0082        | 14.0  | 1582 | 0.6033          | 0.83     |
-| 0.0072        | 15.0  | 1695 | 0.5752          | 0.83     |
+| 0.7581        | 1.0   | 56   | 0.7029          | 0.78     |
+| 0.3942        | 1.99  | 112  | 0.4646          | 0.86     |
+| 0.3298        | 2.99  | 168  | 0.3861          | 0.88     |
+| 0.1227        | 4.0   | 225  | 0.4702          | 0.86     |
+| 0.0774        | 5.0   | 281  | 0.4492          | 0.9      |
+| 0.0039        | 5.99  | 337  | 0.4607          | 0.9      |
+| 0.0014        | 6.99  | 393  | 0.5022          | 0.9      |
+| 0.0022        | 8.0   | 450  | 0.4711          | 0.9      |
+| 0.0193        | 9.0   | 506  | 0.5226          | 0.86     |
+| 0.0004        | 9.99  | 562  | 0.6055          | 0.82     |
+| 0.0003        | 10.99 | 618  | 0.4793          | 0.89     |
+| 0.0002        | 12.0  | 675  | 0.5052          | 0.9      |
+| 0.0002        | 13.0  | 731  | 0.4652          | 0.89     |
+| 0.0001        | 13.99 | 787  | 0.4617          | 0.9      |
+| 0.0001        | 14.99 | 843  | 0.4653          | 0.9      |
+| 0.0001        | 16.0  | 900  | 0.4635          | 0.91     |
+| 0.0001        | 17.0  | 956  | 0.4693          | 0.9      |
+| 0.0001        | 17.99 | 1012 | 0.4697          | 0.9      |
+| 0.0001        | 18.99 | 1068 | 0.4715          | 0.9      |
+| 0.0025        | 19.91 | 1120 | 0.4717          | 0.9      |
 
 
 ### Framework versions
 
-- Transformers 4.30.0
+- Transformers 4.31.0.dev0
 - Pytorch 2.0.1+cu118
-- Datasets 2.12.0
+- Datasets 2.13.1
 - Tokenizers 0.13.3

config.json

@@ -1,52 +1,12 @@
 {
-  "_name_or_path": "ntu-spml/distilhubert",
-  "activation_dropout": 0.1,
-  "apply_spec_augment": false,
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
   "architectures": [
-    "HubertForSequenceClassification"
+    "ASTForAudioClassification"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "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,
-  "do_stable_layer_norm": false,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.0,
-  "feat_proj_layer_norm": false,
-  "final_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
     "0": "blues",
@@ -74,23 +34,16 @@
     "reggae": "8",
     "rock": "9"
   },
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "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": "hubert",
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
   "num_attention_heads": 12,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
-  "num_hidden_layers": 2,
-  "pad_token_id": 0,
+  "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": "4.30.0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32
+  "transformers_version": "4.31.0.dev0"
 }

preprocessor_config.json

@@ -1,9 +1,13 @@
 {
   "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_extractor_type": "ASTFeatureExtractor",
   "feature_size": 1,
+  "max_length": 1024,
+  "mean": -4.2677393,
+  "num_mel_bins": 128,
   "padding_side": "right",
-  "padding_value": 0,
-  "return_attention_mask": true,
-  "sampling_rate": 16000
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "std": 4.5689974
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c7ff2fa0a414f601870868e3a609aa033ce737f4453016a85f434bec089417d
-size 94783376
+oid sha256:aaddab9baccf21fdd4b71c5748750967fccfbd7145c9f067636b0798b06c99d8
+size 344860025

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb1e4cd9b526d63fc9658531b0fec58392615665647ca817e210356d56aba70
-size 3963
+oid sha256:820d83430bf5ca24a07288b6880ffe6c418e766a8e4e37faf5d2821727ea8e2f
+size 4027