End of training

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
+tags:
+- generated_from_trainer
+model-index:
+- name: wav2vec2_crema_d_ser
+ 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_crema_d_ser
+
+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:
+- eval_loss: 0.7449
+- eval_accuracy: 0.7211
+- eval_runtime: 93.9018
+- eval_samples_per_second: 15.846
+- eval_steps_per_second: 3.962
+- epoch: 0.86
+- step: 640
+
+## 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: 1.0
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.1.dev0
+- Tokenizers 0.15.2

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": "ANG",
+ "1": "DIS",
+ "2": "FEA",
+ "3": "HAP",
+ "4": "NEU",
+ "5": "SAD"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "label2id": {
+ "ANG": 0,
+ "DIS": 1,
+ "FEA": 2,
+ "HAP": 3,
+ "NEU": 4,
+ "SAD": 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": "4.40.0.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:d14acc4bd5a35b234fa9f130f26ecd7b0c4b52d93bbae07157256d5fdb8ccd90
+size 1266030704

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/Apr14_03-10-16_8836603d0e46/events.out.tfevents.1713064220.8836603d0e46.2101.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd9c19b87a24fc2d84fd41883b14549ac7f1df5fd509a04446b792ef3499068
+size 6783

runs/Apr14_03-10-16_8836603d0e46/events.out.tfevents.1713064239.8836603d0e46.2101.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79037b129122ce34acf18571a186e05d0149f900c0bbd0f47e3ef4ac61bed241
+size 40681

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb61568eef2d2214abd81d877b03191362d71af0e88a130c0ecd75ab8cbbfc5
+size 4920