Upload folder using huggingface_hub

wav2vec-english-speech-emotion-recognition/.gitattributes

@@ -0,0 +1,32 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

wav2vec-english-speech-emotion-recognition/README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model_index:
+  name: wav2vec-english-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.
+
+Several datasets were used the fine-tune the original model:  
+- Surrey Audio-Visual Expressed Emotion [(SAVEE)](http://kahlan.eps.surrey.ac.uk/savee/Database.html) - 480 audio files from 4 male actors
+- Ryerson Audio-Visual Database of Emotional Speech and Song [(RAVDESS)](https://zenodo.org/record/1188976) - 1440 audio files from 24 professional actors (12 female, 12 male)
+- Toronto emotional speech set [(TESS)](https://tspace.library.utoronto.ca/handle/1807/24487) - 2800 audio files from 2 female actors
+
+7 labels/emotions were used as classification labels
+```python
+emotions = ['angry' 'disgust' 'fear' 'happy' 'neutral' 'sad' 'surprise']
+```
+It achieves the following results on the evaluation set:
+- Loss: 0.104075
+- Accuracy: 0.97463
+
+## Model Usage
+```bash
+pip install transformers librosa torch
+```
+```python
+from transformers import *
+import librosa
+import torch
+
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("r-f/wav2vec-english-speech-emotion-recognition")
+model = Wav2Vec2ForCTC.from_pretrained("r-f/wav2vec-english-speech-emotion-recognition")
+
+def predict_emotion(audio_path):
+    audio, rate = librosa.load(audio_path, sr=16000)
+    inputs = feature_extractor(audio, sampling_rate=rate, return_tensors="pt", padding=True)
+    
+    with torch.no_grad():
+        outputs = model(inputs.input_values)
+        predictions = torch.nn.functional.softmax(outputs.logits.mean(dim=1), dim=-1)  # Average over sequence length
+        predicted_label = torch.argmax(predictions, dim=-1)
+        emotion = model.config.id2label[predicted_label.item()]
+    return emotion
+
+emotion = predict_emotion("example_audio.wav")
+print(f"Predicted emotion: {emotion}")
+>> Predicted emotion: angry
+```
+
+
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- eval_steps: 500
+- seed: 42
+- gradient_accumulation_steps: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- num_epochs: 4
+- max_steps=7500
+- save_steps: 1500
+
+### Training results
+| Step | Training Loss | Validation Loss | Accuracy |
+| ---- | ------------- | --------------- | -------- |
+| 500  | 1.8124        | 1.365212        | 0.486258 |
+| 1000 | 0.8872        | 0.773145        | 0.79704  |
+| 1500 | 0.7035        | 0.574954        | 0.852008 |
+| 2000 | 0.6879        | 1.286738        | 0.775899 |
+| 2500 | 0.6498        | 0.697455        | 0.832981 |
+| 3000 | 0.5696        | 0.33724         | 0.892178 |
+| 3500 | 0.4218        | 0.307072        | 0.911205 |
+| 4000 | 0.3088        | 0.374443        | 0.930233 |
+| 4500 | 0.2688        | 0.260444        | 0.936575 |
+| 5000 | 0.2973        | 0.302985        | 0.92389  |
+| 5500 | 0.1765        | 0.165439        | 0.961945 |
+| 6000 | 0.1475        | 0.170199        | 0.961945 |
+| 6500 | 0.1274        | 0.15531         | 0.966173 |
+| 7000 | 0.0699        | 0.103882        | 0.976744 |
+| 7500 | 0.083         | 0.104075        | 0.97463  |

wav2vec-english-speech-emotion-recognition/config.json

@@ -0,0 +1,137 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
+  "processor_class": "Wav2Vec2CTCTokenizer",
+  "activation_dropout": 0.05,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "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": "fear",
+    "3": "happy",
+    "4": "neutral",
+    "5": "sad",
+    "6": "surprise"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "angry": 0,
+    "disgust": 1,
+    "fear": 2,
+    "happy": 3,
+    "neutral": 4,
+    "sad": 5,
+    "surprise": 6
+  },
+  "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": "4.22.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "xvector_output_dim": 512
+}

wav2vec-english-speech-emotion-recognition/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
+}

wav2vec-english-speech-emotion-recognition/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6470434ecf20ae93b22284ac83877984fb8765e332037c36a54df6607e3a206
+size 1266126445

wav2vec-english-speech-emotion-recognition/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7a4b18e6dd098bbeba86991ea3a66623c19570bf00ab392b2b8e7e72ee8598
+size 3439