metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- asvp_esd
metrics:
- accuracy
model-index:
- name: my_awesome_emotion_model
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: asvp_esd
type: asvp_esd
config: ASVP_ESD
split: train
args: ASVP_ESD
metrics:
- name: Accuracy
type: accuracy
value: 0.46430910281597904
my_awesome_emotion_model
This model is a fine-tuned version of facebook/wav2vec2-base on the asvp_esd dataset. It achieves the following results on the evaluation set:
- Loss: 1.7259
- Accuracy: 0.4643
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.4474 | 0.98 | 47 | 2.3539 | 0.2567 |
2.1378 | 1.99 | 95 | 2.1044 | 0.3530 |
2.006 | 2.99 | 143 | 1.9574 | 0.3949 |
1.8966 | 4.0 | 191 | 1.8966 | 0.4060 |
1.851 | 4.98 | 238 | 1.8110 | 0.4348 |
1.7784 | 5.99 | 286 | 1.7655 | 0.4486 |
1.6856 | 6.99 | 334 | 1.7469 | 0.4650 |
1.6076 | 8.0 | 382 | 1.7341 | 0.4558 |
1.6216 | 8.98 | 429 | 1.7312 | 0.4617 |
1.5692 | 9.84 | 470 | 1.7259 | 0.4643 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0