End of training

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-large-xlsr-53-english-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-large-xlsr-53-english-finetuned-ravdess-v8
+
+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: 1.6533
+- Accuracy: 0.7222
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.1363        | 0.15  | 25   | 1.0081          | 0.7778   |
+| 0.1327        | 0.31  | 50   | 0.9010          | 0.8125   |
+| 0.1415        | 0.46  | 75   | 1.4153          | 0.7153   |
+| 0.185         | 0.62  | 100  | 1.7617          | 0.7083   |
+| 0.2158        | 0.77  | 125  | 2.1611          | 0.6597   |
+| 0.4308        | 0.93  | 150  | 2.0827          | 0.6597   |
+| 0.3191        | 1.08  | 175  | 2.2436          | 0.6319   |
+| 0.3377        | 1.23  | 200  | 1.7225          | 0.6944   |
+| 0.232         | 1.39  | 225  | 1.5759          | 0.7292   |
+| 0.2571        | 1.54  | 250  | 1.8838          | 0.7222   |
+| 0.2376        | 1.7   | 275  | 1.5548          | 0.7222   |
+| 0.1417        | 1.85  | 300  | 1.2785          | 0.75     |
+| 0.0731        | 2.01  | 325  | 1.4898          | 0.7431   |
+| 0.0852        | 2.16  | 350  | 1.3757          | 0.75     |
+| 0.0517        | 2.31  | 375  | 1.4918          | 0.7361   |
+| 0.1537        | 2.47  | 400  | 1.4951          | 0.7431   |
+| 0.0309        | 2.62  | 425  | 1.5893          | 0.7292   |
+| 0.0021        | 2.78  | 450  | 1.6348          | 0.7292   |
+| 0.0394        | 2.93  | 475  | 1.6533          | 0.7222   |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,136 @@
+{
+  "_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": [
+    "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,
+  "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,
+  "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 +1,10 @@
+{
+  "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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3e0001652e89a0ddd4b95834b28a0a15cbe7254bc79a46538fb39bdcc58d4e
+size 1262960309

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ecbe92192fda8ada76c2d038193fc385bb27e6679dc98be8fdf7ee2c152ae55
+size 4091