|
--- |
|
license: apache-2.0 |
|
base_model: hughlan1214/SER_wav2vec2-large-xlsr-53_fine-tuned_1.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: SER_wav2vec2-large-xlsr-53_240304_fine-tuned1.1 |
|
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. --> |
|
|
|
# SER_wav2vec2-large-xlsr-53_240304_fin-tuned |
|
|
|
This model is a fine-tuned version of [hughlan1214/SER_wav2vec2-large-xlsr-53_fine-tuned_1.0](https://huggingface.co/hughlan1214/SER_wav2vec2-large-xlsr-53_fine-tuned_1.0) on a [Speech Emotion Recognition (en)](https://www.kaggle.com/datasets/dmitrybabko/speech-emotion-recognition-en) dataset. |
|
|
|
This dataset includes the 4 most popular datasets in English: Crema, Ravdess, Savee, and Tess, containing a total of over 12,000 .wav audio files. Each of these four datasets includes 6 to 8 different emotional labels. |
|
|
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1815 |
|
- Accuracy: 0.5776 |
|
- Precision: 0.6236 |
|
- Recall: 0.5921 |
|
- F1: 0.5806 |
|
|
|
|
|
For a better performance version, please refer to [hughlan1214/Speech_Emotion_Recognition_wav2vec2-large-xlsr-53_240304_SER_fin-tuned2.0](https://huggingface.co/hughlan1214/Speech_Emotion_Recognition_wav2vec2-large-xlsr-53_240304_SER_fin-tuned2.0) |
|
|
|
|
|
## Model description |
|
|
|
|
|
For a better performance version, please refer to [hughlan1214/Speech_Emotion_Recognition_wav2vec2-large-xlsr-53_240304_SER_fin-tuned2.0](https://huggingface.co/hughlan1214/Speech_Emotion_Recognition_wav2vec2-large-xlsr-53_240304_SER_fin-tuned2.0) |
|
|
|
|
|
The model was obtained through feature extraction using [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) and underwent several rounds of fine-tuning. It predicts the 7 types of emotions contained in speech, aiming to lay the foundation for subsequent use of human micro-expressions on the visual level and context semantics under LLMS to infer user emotions in real-time. |
|
|
|
Although the model was trained on purely English datasets, post-release testing showed that it also performs well in predicting emotions in Chinese and French, demonstrating the powerful cross-linguistic capability of the [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) pre-trained model. |
|
|
|
```python |
|
emotions = ['angry', 'disgust', 'fear', 'happy', 'neutral', 'sad', 'surprise'] |
|
``` |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 1.5816 | 1.0 | 1048 | 1.4920 | 0.4392 | 0.4568 | 0.4623 | 0.4226 | |
|
| 1.2355 | 2.0 | 2096 | 1.2957 | 0.5135 | 0.6082 | 0.5292 | 0.5192 | |
|
| 1.0605 | 3.0 | 3144 | 1.2225 | 0.5405 | 0.5925 | 0.5531 | 0.5462 | |
|
| 1.0291 | 4.0 | 4192 | 1.2163 | 0.5586 | 0.6215 | 0.5739 | 0.5660 | |
|
| 1.0128 | 5.0 | 5240 | 1.1815 | 0.5776 | 0.6236 | 0.5921 | 0.5806 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.2.1 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|
