nicekevin/whisper_bs_ft_lgevr2_v3_2

This model is a fine-tuned version of openai/whisper-base on the lgevr_sentence_v2 dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4283
• eval_cer: 12.9976
• eval_runtime: 10.4189
• eval_samples_per_second: 3.743
• eval_steps_per_second: 0.48
• epoch: 25.0
• step: 500

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-06
• 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: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0