End of training

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Wav2Vec2_Fine_tuned_on_RAVDESS_2_Speech_Emotion_Recognition
+  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_Fine_tuned_on_RAVDESS_2_Speech_Emotion_Recognition
+
+This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5638
+- Accuracy: 0.8125
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.1085        | 0.0694 | 10   | 2.0715          | 0.1701   |
+| 2.043         | 0.1389 | 20   | 2.0531          | 0.1944   |
+| 2.0038        | 0.2083 | 30   | 1.9162          | 0.3056   |
+| 1.9217        | 0.2778 | 40   | 1.8085          | 0.3264   |
+| 1.7814        | 0.3472 | 50   | 1.6440          | 0.3611   |
+| 1.5997        | 0.4167 | 60   | 1.5428          | 0.3681   |
+| 1.5293        | 0.4861 | 70   | 1.4812          | 0.4062   |
+| 1.5473        | 0.5556 | 80   | 1.3423          | 0.4826   |
+| 1.5098        | 0.625  | 90   | 1.3632          | 0.4653   |
+| 1.1967        | 0.6944 | 100  | 1.3762          | 0.4618   |
+| 1.2255        | 0.7639 | 110  | 1.3456          | 0.4618   |
+| 1.6152        | 0.8333 | 120  | 1.3206          | 0.4826   |
+| 1.1365        | 0.9028 | 130  | 1.3343          | 0.4792   |
+| 1.1254        | 0.9722 | 140  | 1.2481          | 0.4792   |
+| 1.3486        | 1.0417 | 150  | 1.4024          | 0.4688   |
+| 1.2029        | 1.1111 | 160  | 1.1053          | 0.5556   |
+| 1.0734        | 1.1806 | 170  | 1.1238          | 0.6181   |
+| 1.029         | 1.25   | 180  | 1.3111          | 0.5347   |
+| 1.0955        | 1.3194 | 190  | 1.0256          | 0.6146   |
+| 0.8893        | 1.3889 | 200  | 0.9970          | 0.6389   |
+| 0.8874        | 1.4583 | 210  | 0.9895          | 0.6389   |
+| 0.9227        | 1.5278 | 220  | 0.8335          | 0.6667   |
+| 0.7566        | 1.5972 | 230  | 0.8839          | 0.6944   |
+| 0.8062        | 1.6667 | 240  | 0.8070          | 0.7118   |
+| 0.6773        | 1.7361 | 250  | 0.7592          | 0.7222   |
+| 0.7874        | 1.8056 | 260  | 1.1098          | 0.6285   |
+| 0.8262        | 1.875  | 270  | 0.6952          | 0.7569   |
+| 0.568         | 1.9444 | 280  | 0.7635          | 0.7326   |
+| 0.6914        | 2.0139 | 290  | 0.6607          | 0.7917   |
+| 0.6838        | 2.0833 | 300  | 0.8466          | 0.7049   |
+| 0.6318        | 2.1528 | 310  | 0.6612          | 0.8056   |
+| 0.604         | 2.2222 | 320  | 0.9257          | 0.6667   |
+| 0.5321        | 2.2917 | 330  | 0.6067          | 0.7986   |
+| 0.3421        | 2.3611 | 340  | 0.6594          | 0.7535   |
+| 0.3536        | 2.4306 | 350  | 0.6525          | 0.7812   |
+| 0.3087        | 2.5    | 360  | 0.6412          | 0.7812   |
+| 0.4236        | 2.5694 | 370  | 0.6560          | 0.7812   |
+| 0.5134        | 2.6389 | 380  | 0.6614          | 0.7882   |
+| 0.5709        | 2.7083 | 390  | 0.5989          | 0.8021   |
+| 0.2912        | 2.7778 | 400  | 0.6142          | 0.7951   |
+| 0.516         | 2.8472 | 410  | 0.5926          | 0.7986   |
+| 0.3835        | 2.9167 | 420  | 0.5797          | 0.8125   |
+| 0.4055        | 2.9861 | 430  | 0.5638          | 0.8125   |
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1.dev0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,139 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSpeechClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "wav2vec2_clf",
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "angry",
+    "1": "calm",
+    "2": "disgust",
+    "3": "fearful",
+    "4": "happy",
+    "5": "neutral",
+    "6": "sad",
+    "7": "surprised"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "angry": 0,
+    "calm": 1,
+    "disgust": 2,
+    "fearful": 3,
+    "happy": 4,
+    "neutral": 5,
+    "sad": 6,
+    "surprised": 7
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "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": "4.41.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb4b678f325e1c2e82b153708bb632b2d93657db76347ea4c1752e300de365a
+size 1266038904

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Apr20_04-49-47_d3/events.out.tfevents.1713581408.d3.148841.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59689d01466f4b9dd80000d6299d266038873e068d503d1eee3404751b8c2fc
+size 7058

runs/Apr20_04-50-45_d3/events.out.tfevents.1713581448.d3.148841.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1614cea7821dcb9cc7ddc74f23c870758f113c226ea5babc88bd13ac7012039a
+size 88

runs/Apr20_04-53-04_d3/events.out.tfevents.1713581588.d3.149121.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087677c749c9fc77d57788d410e69662ef6389ddc322a943228ca470aa8036af
+size 30047

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1799f1c3a5c3401cc79ce64a6ac46752721f3a09c041f1d9de4f2e9997eb206
+size 5048