metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - arrow
metrics:
  - wer
model-index:
  - name: demo_whisper
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: arrow
          type: arrow
          config: default
          split: None
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 47.00413223140496

demo_whisper

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

Loss: 0.6383
Wer Ortho: 59.3622
Wer: 47.0041

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: 2e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 500
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cpu
Datasets 3.0.0
Tokenizers 0.19.1