Hugging Face's logo

mn367
/
whisper-medium-1hr

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
English
whisper
en-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
whisper-medium-1hr / README.md
mn367's picture
mn367
update model card README.md
e35e07f
preview code
|
raw
history blame contribute delete
1.39 kB
metadata
language:
  - en
license: apache-2.0
tags:
  - en-asr-leaderboard
  - generated_from_trainer
datasets:
  - mn367/radio-test-dataset
model-index:
  - name: Whisper Medium 1hr
    results: []

Whisper Medium 1hr

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

  • eval_loss: 0.6053
  • eval_wer: 17.5426
  • eval_runtime: 651.6941
  • eval_samples_per_second: 2.363
  • eval_steps_per_second: 0.296
  • epoch: 37.5
  • step: 900

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: 1e-06
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 1600
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2