Hugging Face's logo

devkyle
/
base-v3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
base-v3 / README.md
devkyle's picture
devkyle
End of training
e6840ef verified
preview code
|
raw
history blame contribute delete
1.64 kB
metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-base-v3
    results: []

whisper-base-v3

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8131
  • Wer: 54.6363

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-05
  • 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: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
3.0483 10.0 500 2.3813 300.7007
1.4107 20.0 1000 1.0215 72.7639
0.961 30.0 1500 0.8458 58.4079
0.8576 40.0 2000 0.8131 54.6363

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.2
  • Tokenizers 0.20.1