Model save

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+model-index:
+- name: deepfake_audio_wav2vec
+  results: []
+---
+
+<!-- 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. -->
+
+# deepfake_audio_wav2vec
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.94,
+    "eval_loss": 0.2446485459804535,
+    "eval_runtime": 10.3634,
+    "eval_samples_per_second": 9.649,
+    "eval_steps_per_second": 0.675,
+    "total_flos": 3.183758365185645e+17,
+    "train_loss": 0.0,
+    "train_runtime": 0.0041,
+    "train_samples_per_second": 7348.544,
+    "train_steps_per_second": 734.854
+}

config.json

@@ -0,0 +1,126 @@
+{
+  "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,
+  "finetuning_task": "audio-classification",
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "spoof",
+    "1": "bona-fide"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bona-fide": "1",
+    "spoof": "0"
+  },
+  "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": "4.52.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

eval_detailed_metrics.json

@@ -0,0 +1,55 @@
+{
+  "confusion_matrix": [
+    [
+      30,
+      5
+    ],
+    [
+      1,
+      64
+    ]
+  ],
+  "classification_report": {
+    "spoof": {
+      "precision": 0.967741935483871,
+      "recall": 0.8571428571428571,
+      "f1-score": 0.9090909090909091,
+      "support": 35.0
+    },
+    "bona-fide": {
+      "precision": 0.927536231884058,
+      "recall": 0.9846153846153847,
+      "f1-score": 0.9552238805970149,
+      "support": 65.0
+    },
+    "accuracy": 0.94,
+    "macro avg": {
+      "precision": 0.9476390836839645,
+      "recall": 0.9208791208791209,
+      "f1-score": 0.932157394843962,
+      "support": 100.0
+    },
+    "weighted avg": {
+      "precision": 0.9416082281439926,
+      "recall": 0.94,
+      "f1-score": 0.9390773405698779,
+      "support": 100.0
+    }
+  },
+  "classification_report_str": "              precision    recall  f1-score   support\n\n       spoof     0.9677    0.8571    0.9091        35\n   bona-fide     0.9275    0.9846    0.9552        65\n\n    accuracy                         0.9400       100\n   macro avg     0.9476    0.9209    0.9322       100\nweighted avg     0.9416    0.9400    0.9391       100\n",
+  "per_class_accuracy": {
+    "spoof": 0.8571428571428571,
+    "bona-fide": 0.9846153846153847
+  },
+  "task": {
+    "name": "Audio Classification",
+    "type": "audio-classification"
+  },
+  "metrics": [
+    {
+      "name": "Accuracy",
+      "type": "accuracy",
+      "value": 0.94
+    }
+  ]
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.94,
+    "eval_loss": 0.2446485459804535,
+    "eval_runtime": 10.3634,
+    "eval_samples_per_second": 9.649,
+    "eval_steps_per_second": 0.675
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afd58df46a22377f0cc5858e872785b35e5cf5e16fcc71ac4a1d020c342b26c
+size 378302360

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": true,
+  "sampling_rate": 16000
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.183758365185645e+17,
+    "train_loss": 0.0,
+    "train_runtime": 0.0041,
+    "train_samples_per_second": 7348.544,
+    "train_steps_per_second": 734.854
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 189,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 189,
+      "total_flos": 3.183758365185645e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.0041,
+      "train_samples_per_second": 7348.544,
+      "train_steps_per_second": 734.854
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.183758365185645e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69af193f7d8bfe1f51f53d9ea33041f36bd54510a1680c42745f52174027223f
+size 5368