README.md

metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - uzh-math-seminarlive/test-finetuning
model-index:
  - name: Whisper Small Math Test - paul891112
    results: []

Whisper Small Math Test - paul891112

This model is a fine-tuned version of openai/whisper-small on the Test dataset for fine-tuning dataset.

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: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.25	10	0.4637	26.5957

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.15.2