whisper_tiny_24til

This model is a fine-tuned version of casual/whisper_tiny_24til on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0000
• eval_wer: 2.6755
• eval_runtime: 782.4199
• eval_samples_per_second: 4.473
• eval_steps_per_second: 0.56
• epoch: 6.8493
• step: 1500

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• training_steps: 4000

Framework versions

• Transformers 4.40.2
• Pytorch 2.0.1+cu117
• Datasets 2.19.1
• Tokenizers 0.19.1