Upload 5 files

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model_index:
+  name: wav2vec2-lg-xlsr-en-speech-emotion-recognition
+---
+
+# Speech Emotion Recognition By Fine-Tuning Wav2Vec 2.0
+
+The model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) for a Speech Emotion Recognition (SER) task.
+
+The dataset used to fine-tune the original pre-trained model is the [RAVDESS dataset](https://zenodo.org/record/1188976#.YO6yI-gzaUk). This dataset provides 1440 samples of recordings from actors performing on 8 different emotions in English, which are:
+
+```python
+emotions = ['angry', 'calm', 'disgust', 'fearful', 'happy', 'neutral', 'sad', 'surprised']
+```
+
+It achieves the following results on the evaluation set:
+- Loss: 0.5023
+- Accuracy: 0.8223
+
+## 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.0752        | 0.21  | 30   | 2.0505          | 0.1359   |
+| 2.0119        | 0.42  | 60   | 1.9340          | 0.2474   |
+| 1.8073        | 0.63  | 90   | 1.5169          | 0.3902   |
+| 1.5418        | 0.84  | 120  | 1.2373          | 0.5610   |
+| 1.1432        | 1.05  | 150  | 1.1579          | 0.5610   |
+| 0.9645        | 1.26  | 180  | 0.9610          | 0.6167   |
+| 0.8811        | 1.47  | 210  | 0.8063          | 0.7178   |
+| 0.8756        | 1.68  | 240  | 0.7379          | 0.7352   |
+| 0.8208        | 1.89  | 270  | 0.6839          | 0.7596   |
+| 0.7118        | 2.1   | 300  | 0.6664          | 0.7735   |
+| 0.4261        | 2.31  | 330  | 0.6058          | 0.8014   |
+| 0.4394        | 2.52  | 360  | 0.5754          | 0.8223   |
+| 0.4581        | 2.72  | 390  | 0.4719          | 0.8467   |
+| 0.3967        | 2.93  | 420  | 0.5023          | 0.8223   |
+
+## Contact
+
+Any doubt, contact me on [Twitter](https://twitter.com/ehcalabres) (GitHub repo soon).
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.9.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
+  "activation_dropout": 0.05,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "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",
+  "gradient_checkpointing": true,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "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,
+  "pad_token_id": 0,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "proj_codevector_dim": 256,
+  "transformers_version": "4.8.2",
+  "vocab_size": 33
+}

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 sha256:51f2f61d0b1e09d7873ad2ef6a287f99b8e11ad1d2ee44d8278940e952270f03
+size 1266155629

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d0e655c82ce458316cab3dff37a9cc7cf70d03b7f98b5fa338642876e3733f
+size 2863