superb_ks_42

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

  • Loss: 0.1434
  • Accuracy: 0.9801

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: 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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.8486 1.0 1597 0.2380 0.9385
0.0986 2.0 3194 0.1777 0.9598
0.0773 3.0 4791 0.1249 0.9738
0.0532 4.0 6388 0.1078 0.9782
0.0472 5.0 7985 0.1258 0.9766
0.0322 6.0 9582 0.1365 0.9772
0.0258 7.0 11179 0.1338 0.9798
0.0231 8.0 12776 0.1447 0.9796
0.0171 9.0 14373 0.1435 0.9797
0.0142 10.0 15970 0.1434 0.9801

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
11
Safetensors
Model size
8.31M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for jialicheng/whisper-tiny-speech_commands

Finetuned
(1256)
this model

Dataset used to train jialicheng/whisper-tiny-speech_commands

Collection including jialicheng/whisper-tiny-speech_commands

Evaluation results