whisper-tiny-ru

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

• Loss: 1.2475
• Wer: 83.7270

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: 8
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 40
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9999	4.4444	40	1.2054	71.8285
0.4535	8.8889	80	1.1539	73.2283
0.2849	13.3333	120	1.1958	104.5494
0.1674	17.7778	160	1.2341	79.2651
0.1372	22.2222	200	1.2475	83.7270

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1