Hugging Face's logo

Bedru
/
whisper-small-wello-lora

PEFT
TensorBoard
Safetensors
Transformers
Amharic
lora
Eval Results (legacy)
Model card Files
xet
 Metrics Community

Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string

Whisper Small am - Bedru Yimam

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

  • Loss: 0.8734
  • Wer: 101.1385

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.4531 1.7301 500 1.2242 107.7109
2.0232 3.4602 1000 1.0240 101.9665
1.8241 5.1903 1500 0.9223 105.7444
1.7149 6.9204 2000 0.8734 101.1385

Framework versions

  • PEFT 0.18.1
  • Transformers 5.0.0
  • Pytorch 2.10.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2
Downloads last month
2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Bedru/whisper-small-wello-lora

Base model

openai/whisper-small
Adapter
(270)
this model

Dataset used to train Bedru/whisper-small-wello-lora

Evaluation results