|
--- |
|
license: apache-2.0 |
|
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- narad/ravdess |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: wav2vec2-large-xlsr-53-english-finetuned-ravdess |
|
results: |
|
- task: |
|
name: Audio Classification |
|
type: audio-classification |
|
dataset: |
|
name: RAVDESS |
|
type: narad/ravdess |
|
config: all |
|
split: train |
|
args: all |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8298611111111112 |
|
- name: Precision |
|
type: precision |
|
value: 0.8453025128787324 |
|
- name: Recall |
|
type: recall |
|
value: 0.8298611111111112 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8329568451751053 |
|
--- |
|
|
|
<!-- 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 |
|
|
|
This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on the RAVDESS dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5624 |
|
- Accuracy: 0.8299 |
|
- Precision: 0.8453 |
|
- Recall: 0.8299 |
|
- F1: 0.8330 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 1.9765 | 1.0 | 288 | 1.9102 | 0.3090 | 0.3203 | 0.3090 | 0.1941 | |
|
| 1.4803 | 2.0 | 576 | 1.4590 | 0.5660 | 0.5493 | 0.5660 | 0.4811 | |
|
| 1.1625 | 3.0 | 864 | 1.2308 | 0.6215 | 0.6299 | 0.6215 | 0.5936 | |
|
| 0.8354 | 4.0 | 1152 | 0.7821 | 0.7222 | 0.7555 | 0.7222 | 0.6869 | |
|
| 0.2066 | 5.0 | 1440 | 0.7910 | 0.7708 | 0.8373 | 0.7708 | 0.7881 | |
|
| 0.6335 | 6.0 | 1728 | 0.5624 | 0.8299 | 0.8453 | 0.8299 | 0.8330 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
