README.md

metadata

library_name: peft
language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper small NSC part 1,2,3 (50 steps) - Jarrett Er
    results: []

Whisper small NSC part 1,2,3 (50 steps) - Jarrett Er

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: 0.2571
• Wer: 8.4236

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: 16
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• training_steps: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3427	1.22	50	0.2571	8.4236

Framework versions

• PEFT 0.14.0
• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.1.dev0
• Tokenizers 0.20.3