Hugging Face's logo

acroma
/
output_dir

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
whisper-event
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
output_dir / README.md
acroma's picture
acroma
End of training
d657e5f verified
preview code
|
raw
history blame contribute delete
1.72 kB
metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - whisper-event
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: output_dir
    results: []

output_dir

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

  • Loss: 1.9972
  • Wer: 99.4455

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: 2
  • eval_batch_size: 2
  • 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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
1.9297 1.0152 1000 1.9972 99.4455
1.1678 2.0305 2000 1.9989 99.4455
0.5123 3.0457 3000 2.0867 102.4030
0.2025 4.0609 4000 2.1698 103.3272
0.0843 5.0761 5000 2.2214 104.2514

Framework versions

  • Transformers 4.44.1
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1