metadata

license: apache-2.0
base_model: openai/whisper-base.en
tags:
  - generated_from_trainer
datasets:
  - speech_commands
metrics:
  - accuracy
model-index:
  - name: whisper-base.en-speech-commands
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: speech_commands
          type: speech_commands
          config: v0.02
          split: None
          args: v0.02
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8053057553956835

whisper-base.en-speech-commands

This model is a fine-tuned version of openai/whisper-base.en on the speech_commands dataset. It achieves the following results on the evaluation set:

Loss: 1.1288
Accuracy: 0.8053

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: 96
eval_batch_size: 96
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: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2727	1.0	412	0.9931	0.8031
0.1816	2.0	824	1.1288	0.8053
0.1323	3.0	1236	1.0521	0.8008
0.0551	4.0	1648	1.0061	0.7999
0.0653	5.0	2060	0.9538	0.8017
0.0489	6.0	2472	1.0026	0.8017
0.0326	7.0	2884	1.0090	0.8031

Framework versions

Transformers 4.43.3
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.19.1