End of training

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base-960h
+tags:
+- audio-classification
+- deepfake
+- audio-spoof
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-base-960h-itw-deepfake
+  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. -->
+
+# wav2vec2-base-960h-itw-deepfake
+
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0917
+- Accuracy: 0.9835
+- Far: 0.0068
+- Frr: 0.0330
+- Eer: 0.0199
+
+## 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: 1e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Far    | Frr    | Eer    |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|
+| 0.6363        | 0.39  | 2500  | 0.4678          | 0.8652   | 0.0178 | 0.3326 | 0.1752 |
+| 0.2896        | 0.79  | 5000  | 0.1145          | 0.9744   | 0.0170 | 0.0402 | 0.0286 |
+| 0.1554        | 1.18  | 7500  | 0.1024          | 0.9797   | 0.0100 | 0.0377 | 0.0238 |
+| 0.1327        | 1.57  | 10000 | 0.0945          | 0.9825   | 0.0070 | 0.0351 | 0.0211 |
+| 0.13          | 1.97  | 12500 | 0.0917          | 0.9835   | 0.0068 | 0.0330 | 0.0199 |
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.2.dev0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,120 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "finetuning_task": "wav2vec2_clf",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "bona-fide",
+    "1": "spoof"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bona-fide": 0,
+    "spoof": 1
+  },
+  "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,
+  "pooling_mode": "mean",
+  "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.dev0",
+  "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 sha256:0acca7cfc4fd790b1fb7cad4017606fa93e7a0ef030f0c2e2e5d426fb91af272
+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": false,
+  "sampling_rate": 16000
+}

runs/Jan25_16-30-15_38073bf969c7/events.out.tfevents.1706200216.38073bf969c7.3428.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ea291a9a1fe3a15f40823f926b71b0ca83f2162ac58734eee514e8d6dc8882
+size 9543

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5acd7d8b89d459dec3a2d85f9371de843ece2afde342766895bf072e19e712d
+size 4792