Hugging Face's logo

Enpas
/
opus-base5

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
opus-base5 / README.md
Enpas's picture
Enpas
End of training
e7a67cb verified
preview code
|
raw
history blame contribute delete
No virus
1.6 kB
metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: opus-base
    results: []

opus-base

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

  • Loss: 0.0177
  • Wer: 14.6250

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: 2e-05
  • train_batch_size: 24
  • 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: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0281 0.4075 500 0.0224 18.3943
0.0292 0.8150 1000 0.0209 17.6027
0.0241 1.2225 1500 0.0188 15.7181
0.0197 1.6300 2000 0.0177 14.6250

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.20.0
  • Tokenizers 0.19.1