metadata

library_name: transformers
license: apache-2.0
base_model: imrajeshkr/distilhubert-finetuned-speech_commands
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - precision
  - recall
  - f1
model-index:
  - name: >-
      distilhubert-finetuned-speech_commands-finetuned-englishalphabets-classification
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.9855379188712521
          - name: Recall
            type: recall
            value: 0.9827160493827161
          - name: F1
            type: f1
            value: 0.9825011002108681

distilhubert-finetuned-speech_commands-finetuned-englishalphabets-classification

This model is a fine-tuned version of imrajeshkr/distilhubert-finetuned-speech_commands on the audiofolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0563
Precision: 0.9855
Recall: 0.9827
F1: 0.9825

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: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.2886	1.0	1216	0.2477	0.9098	0.9284	0.9127
0.1426	2.0	2432	0.0792	0.9835	0.9802	0.9795
0.0678	3.0	3648	0.0601	0.9827	0.9790	0.9780
0.0062	4.0	4864	0.0601	0.9848	0.9815	0.9812
0.027	5.0	6080	0.0563	0.9855	0.9827	0.9825

Framework versions

Transformers 4.47.1
Pytorch 2.2.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0