Supreeta03/wav2vec2-base-sentimentAnalysis-CREMA

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wav2vec-best-CREMA-sentiment-analysis-best3
+  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. -->
+
+# wav2vec-best-CREMA-sentiment-analysis-best3
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Top2 Accuracy: 0.7824
+- Loss: 1.1563
+- Accuracy: 0.5601
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Top2 Accuracy | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:-------------:|:---------------:|:--------:|
+| 1.7555        | 0.99  | 37   | 0.5281        | 1.7048          | 0.2905   |
+| 1.5612        | 1.99  | 74   | 0.5819        | 1.5406          | 0.3493   |
+| 1.4333        | 2.98  | 111  | 0.6373        | 1.4668          | 0.3778   |
+| 1.3933        | 4.0   | 149  | 0.6809        | 1.3798          | 0.4450   |
+| 1.3418        | 4.99  | 186  | 0.7045        | 1.3120          | 0.4719   |
+| 1.2238        | 5.99  | 223  | 0.7263        | 1.2718          | 0.4979   |
+| 1.1896        | 6.98  | 260  | 0.7313        | 1.2430          | 0.5113   |
+| 1.1501        | 8.0   | 298  | 0.7296        | 1.2631          | 0.5088   |
+| 1.1052        | 8.99  | 335  | 0.7506        | 1.2462          | 0.5097   |
+| 1.068         | 9.99  | 372  | 0.7641        | 1.1822          | 0.5399   |
+| 1.0594        | 10.98 | 409  | 0.7590        | 1.1700          | 0.5575   |
+| 0.9519        | 12.0  | 447  | 0.7733        | 1.1465          | 0.5516   |
+| 0.9513        | 12.99 | 484  | 0.7918        | 1.1428          | 0.5676   |
+| 0.9324        | 13.99 | 521  | 0.7666        | 1.1721          | 0.5634   |
+| 0.9173        | 14.98 | 558  | 0.7825        | 1.1494          | 0.5584   |
+| 0.8781        | 16.0  | 596  | 0.7918        | 1.1468          | 0.5718   |
+| 0.8627        | 16.99 | 633  | 0.7775        | 1.1554          | 0.5575   |
+| 0.83          | 17.99 | 670  | 0.7817        | 1.1438          | 0.5718   |
+| 0.8305        | 18.98 | 707  | 0.7935        | 1.1323          | 0.5760   |
+| 0.8314        | 19.87 | 740  | 0.7851        | 1.1341          | 0.5726   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,134 @@
+{
+  "_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": "Anger",
+    "1": "Happy",
+    "2": "Fear",
+    "3": "Sad",
+    "4": "Disgust",
+    "5": "Neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Anger": 0,
+    "Disgust": 4,
+    "Fear": 2,
+    "Happy": 1,
+    "Neutral": 5,
+    "Sad": 3
+  },
+  "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": "4.38.2",
+  "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 sha256:5548cb17787c54702f06c19fd2a08f8b75ae87f3455e9f77fd6f2c4e8f6066d2
+size 378306480

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/Apr11_12-04-38_734dde6e3296/events.out.tfevents.1712837085.734dde6e3296.193.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a533a180209e785e7c5fb593799290c23e5503e21922cc96cdf1e6d7f63101
+size 30100

runs/Apr11_12-04-38_734dde6e3296/events.out.tfevents.1712840184.734dde6e3296.193.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1d3b65caa7e3fcc9c018a54ea81360072b4b64147aa4e983616f5a3a6875f9
+size 468

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba89eead0e34d40b3e04e5c43264409a84a152971c22689e44917c265aa6d0b5
+size 4984