whisper-tiny-finetuned

This model is a fine-tuned version of openai/whisper-tiny on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

• eval_loss: 5.3136
• eval_wer: 83.6538
• eval_runtime: 4.0676
• eval_samples_per_second: 2.458
• eval_steps_per_second: 0.738
• epoch: 3.07
• step: 10

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• training_steps: 15
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.2
• Pytorch 2.2.2+cu121
• Datasets 2.19.2
• Tokenizers 0.15.2