mizoru/whisper-small-ru-ORD_0.2_0.1

Whisper Small Ru ORD - Mizoru

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

• epoch: 4.0
• eval_cer: 27.8291
• eval_clean_cer: 22.5350
• eval_clean_wer: 38.3356
• eval_loss: 1.0160
• eval_runtime: 782.5354
• eval_samples_per_second: 0.732
• eval_steps_per_second: 0.092
• eval_wer: 45.6111
• step: 2292

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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2