Hugging Face's logo

ruisp
/
whisper-tiny

Automatic Speech Recognition
Transformers
PyTorch
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
whisper-tiny / README.md
ruisp's picture
ruisp
End of training
0264b18
preview code
|
raw
history blame
1.4 kB
metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
model-index:
  - name: whisper-tiny-ft-PolyAI-minds-14-enUS
    results: []

whisper-tiny-ft-PolyAI-minds-14-enUS

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.6973
  • eval_wer_ortho: 0.5534
  • eval_wer: 0.5537
  • eval_runtime: 30.7251
  • eval_samples_per_second: 3.678
  • eval_steps_per_second: 0.26
  • epoch: 14.29
  • step: 400

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: 4e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: polynomial
  • lr_scheduler_warmup_steps: 150
  • training_steps: 1000

Framework versions

  • Transformers 4.33.0
  • Pytorch 1.12.1+cu116
  • Datasets 2.14.4
  • Tokenizers 0.12.1