End of training

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-lg-xlsr-en-speech-emotion-recognition-finetuned-ravdess-v8
+  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-lg-xlsr-en-speech-emotion-recognition-finetuned-ravdess-v8
+
+This model is a fine-tuned version of [ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://huggingface.co/ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6778
+- Accuracy: 0.75
+
+## 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
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.0178        | 0.15  | 25   | 1.8431          | 0.6181   |
+| 1.7082        | 0.31  | 50   | 1.5052          | 0.5833   |
+| 1.4444        | 0.46  | 75   | 1.3458          | 0.5972   |
+| 1.3888        | 0.62  | 100  | 1.2760          | 0.5972   |
+| 1.1819        | 0.77  | 125  | 1.1075          | 0.6667   |
+| 1.1615        | 0.93  | 150  | 1.0666          | 0.625    |
+| 1.1659        | 1.08  | 175  | 1.3450          | 0.5694   |
+| 0.9798        | 1.23  | 200  | 0.9866          | 0.6528   |
+| 0.9893        | 1.39  | 225  | 0.9311          | 0.6806   |
+| 0.9357        | 1.54  | 250  | 0.9783          | 0.6736   |
+| 0.7998        | 1.7   | 275  | 0.7924          | 0.7014   |
+| 0.7444        | 1.85  | 300  | 0.8980          | 0.6806   |
+| 0.7648        | 2.01  | 325  | 0.8994          | 0.7153   |
+| 0.607         | 2.16  | 350  | 0.9416          | 0.6597   |
+| 0.5551        | 2.31  | 375  | 0.7791          | 0.7431   |
+| 0.5495        | 2.47  | 400  | 0.7665          | 0.7431   |
+| 0.5498        | 2.62  | 425  | 0.8017          | 0.7222   |
+| 0.4887        | 2.78  | 450  | 0.6967          | 0.7639   |
+| 0.5308        | 2.93  | 475  | 0.6857          | 0.7569   |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,139 @@
+{
+  "_name_or_path": "ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
+  "activation_dropout": 0.05,
+  "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": 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": "neutral",
+    "1": "calm",
+    "2": "happy",
+    "3": "sad",
+    "4": "angry",
+    "5": "fearful",
+    "6": "disgust",
+    "7": "surprised"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "angry": "4",
+    "calm": "1",
+    "disgust": "6",
+    "fearful": "5",
+    "happy": "2",
+    "neutral": "0",
+    "sad": "3",
+    "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": "4.32.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "xvector_output_dim": 512
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48a853164f6ea5bd6f25ad5d8843f765efebd45115e463422bc2a396951f6ed
+size 1262960309

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216b25f11a7a0dffde355943dedec4781f0e1e4a42282be7ae94ae5c302ce1e4
+size 4155