Upload 12 files

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,135 @@
+{
+  "_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": "disgust",
+    "2": "fearful",
+    "3": "happy",
+    "4": "sad",
+    "5": "surprised"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "angry": 0,
+    "disgust": 1,
+    "fearful": 2,
+    "happy": 3,
+    "sad": 4,
+    "surprised": 5
+  },
+  "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": "4.34.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "xvector_output_dim": 512
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b9c09437598a239f7b28b67b0ee380642268eb42d0a6f1a15d0e9d308da7ce
+size 2498606983

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": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea2d85778fa3fa694a2fce7af4a12b267d6993a3b1daea0343149a89289fa15
+size 1266125557

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af702ba6a1992546f8fc6cef18e4e1a8821e1fbaa235afba71052ad19ac5a47f
+size 14639

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab279f3efd3ea033873777575fd8387b238c97d8e00e25e22376fb4dd31ee2d
+size 627

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.8854166666666666,
+  "best_model_checkpoint": "/content/drive/MyDrive/Areej/Emotions/wav2vec2-xlsr-speech-emotion-recognition/checkpoint-720",
+  "epoch": 6.0,
+  "eval_steps": 120,
+  "global_step": 720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-05,
+      "loss": 1.482,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.59375,
+      "eval_f1": 0.5526197615888555,
+      "eval_loss": 1.1192463636398315,
+      "eval_precision": 0.6706955283551027,
+      "eval_precision_ang": 0.8571428571428571,
+      "eval_precision_dis": 0.62,
+      "eval_precision_fear": 1.0,
+      "eval_precision_hap": 0.42857142857142855,
+      "eval_precision_sad": 0.3617021276595745,
+      "eval_precision_sur": 0.7567567567567568,
+      "eval_recall": 0.59375,
+      "eval_recall_ang": 0.75,
+      "eval_recall_dis": 0.96875,
+      "eval_recall_fear": 0.0625,
+      "eval_recall_hap": 0.375,
+      "eval_recall_sad": 0.53125,
+      "eval_recall_sur": 0.875,
+      "eval_runtime": 26.0764,
+      "eval_samples_per_second": 7.363,
+      "eval_steps_per_second": 1.841,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8e-05,
+      "loss": 0.7879,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.65625,
+      "eval_f1": 0.6157556418699938,
+      "eval_loss": 0.8884664177894592,
+      "eval_precision": 0.6945893295893296,
+      "eval_precision_ang": 1.0,
+      "eval_precision_dis": 0.7567567567567568,
+      "eval_precision_fear": 0.6904761904761905,
+      "eval_precision_hap": 0.44,
+      "eval_precision_sad": 0.6666666666666666,
+      "eval_precision_sur": 0.6136363636363636,
+      "eval_recall": 0.65625,
+      "eval_recall_ang": 0.15625,
+      "eval_recall_dis": 0.875,
+      "eval_recall_fear": 0.90625,
+      "eval_recall_hap": 0.34375,
+      "eval_recall_sad": 0.8125,
+      "eval_recall_sur": 0.84375,
+      "eval_runtime": 25.9958,
+      "eval_samples_per_second": 7.386,
+      "eval_steps_per_second": 1.846,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7e-05,
+      "loss": 0.4891,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8072916666666666,
+      "eval_f1": 0.8067968655458517,
+      "eval_loss": 0.5996339917182922,
+      "eval_precision": 0.8322896986054881,
+      "eval_precision_ang": 1.0,
+      "eval_precision_dis": 0.8157894736842105,
+      "eval_precision_fear": 0.96,
+      "eval_precision_hap": 0.8571428571428571,
+      "eval_precision_sad": 0.6428571428571429,
+      "eval_precision_sur": 0.717948717948718,
+      "eval_recall": 0.8072916666666666,
+      "eval_recall_ang": 0.84375,
+      "eval_recall_dis": 0.96875,
+      "eval_recall_fear": 0.75,
+      "eval_recall_hap": 0.5625,
+      "eval_recall_sad": 0.84375,
+      "eval_recall_sur": 0.875,
+      "eval_runtime": 26.1555,
+      "eval_samples_per_second": 7.341,
+      "eval_steps_per_second": 1.835,
+      "step": 360
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6e-05,
+      "loss": 0.2076,
+      "step": 480
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8229166666666666,
+      "eval_f1": 0.824936436825434,
+      "eval_loss": 0.6778392195701599,
+      "eval_precision": 0.8481715787566851,
+      "eval_precision_ang": 0.9666666666666667,
+      "eval_precision_dis": 0.9285714285714286,
+      "eval_precision_fear": 0.9583333333333334,
+      "eval_precision_hap": 0.8461538461538461,
+      "eval_precision_sad": 0.6595744680851063,
+      "eval_precision_sur": 0.7297297297297297,
+      "eval_recall": 0.8229166666666666,
+      "eval_recall_ang": 0.90625,
+      "eval_recall_dis": 0.8125,
+      "eval_recall_fear": 0.71875,
+      "eval_recall_hap": 0.6875,
+      "eval_recall_sad": 0.96875,
+      "eval_recall_sur": 0.84375,
+      "eval_runtime": 25.9983,
+      "eval_samples_per_second": 7.385,
+      "eval_steps_per_second": 1.846,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5e-05,
+      "loss": 0.1506,
+      "step": 600
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7708333333333334,
+      "eval_f1": 0.7632545320531495,
+      "eval_loss": 0.9791532158851624,
+      "eval_precision": 0.8025539275539275,
+      "eval_precision_ang": 1.0,
+      "eval_precision_dis": 0.8611111111111112,
+      "eval_precision_fear": 0.9285714285714286,
+      "eval_precision_hap": 0.6153846153846154,
+      "eval_precision_sad": 0.6666666666666666,
+      "eval_precision_sur": 0.7435897435897436,
+      "eval_recall": 0.7708333333333334,
+      "eval_recall_ang": 0.78125,
+      "eval_recall_dis": 0.96875,
+      "eval_recall_fear": 0.40625,
+      "eval_recall_hap": 0.75,
+      "eval_recall_sad": 0.8125,
+      "eval_recall_sur": 0.90625,
+      "eval_runtime": 25.9432,
+      "eval_samples_per_second": 7.401,
+      "eval_steps_per_second": 1.85,
+      "step": 600
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0729,
+      "step": 720
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8854166666666666,
+      "eval_f1": 0.8861592068806491,
+      "eval_loss": 0.519017219543457,
+      "eval_precision": 0.8936954746089651,
+      "eval_precision_ang": 0.9655172413793104,
+      "eval_precision_dis": 0.9090909090909091,
+      "eval_precision_fear": 0.9629629629629629,
+      "eval_precision_hap": 0.9310344827586207,
+      "eval_precision_sad": 0.8157894736842105,
+      "eval_precision_sur": 0.7777777777777778,
+      "eval_recall": 0.8854166666666666,
+      "eval_recall_ang": 0.875,
+      "eval_recall_dis": 0.9375,
+      "eval_recall_fear": 0.8125,
+      "eval_recall_hap": 0.84375,
+      "eval_recall_sad": 0.96875,
+      "eval_recall_sur": 0.875,
+      "eval_runtime": 25.4794,
+      "eval_samples_per_second": 7.535,
+      "eval_steps_per_second": 1.884,
+      "step": 720
+    }
+  ],
+  "logging_steps": 120,
+  "max_steps": 1200,
+  "num_train_epochs": 10,
+  "save_steps": 120,
+  "total_flos": 7.069718492298435e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4e0cc0ff80ca4e79ff17f686efc6762b9068e1806d8f21cb2494b5149ac006
+size 4091

vocab.json

@@ -0,0 +1,35 @@
+{
+  "'": 5,
+  "-": 6,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "a": 7,
+  "b": 8,
+  "c": 9,
+  "d": 10,
+  "e": 11,
+  "f": 12,
+  "g": 13,
+  "h": 14,
+  "i": 15,
+  "j": 16,
+  "k": 17,
+  "l": 18,
+  "m": 19,
+  "n": 20,
+  "o": 21,
+  "p": 22,
+  "q": 23,
+  "r": 24,
+  "s": 25,
+  "t": 26,
+  "u": 27,
+  "v": 28,
+  "w": 29,
+  "x": 30,
+  "y": 31,
+  "z": 32,
+  "|": 4
+}