README.md

metadata

language:
  - ger
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Small Ger - Daniel Dumschat
    results: []

Whisper Small Ger - Daniel Dumschat

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5311
• eval_wer: 91.3258
• eval_runtime: 990.1974
• eval_samples_per_second: 1.624
• eval_steps_per_second: 0.203
• epoch: 0.29
• step: 900

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0