whisper-small-ru-ORD_0.7_peft_0.3

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

Whisper Small Ru ORD 0.7 PEFT LoRA - Mizoru

This model is a fine-tuned version of openai/whisper-small on the ORD_0.7 dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.3021
• eval_wer: 60.8525
• eval_cer: 33.9271
• eval_clean_wer: 53.2332
• eval_clean_cer: 28.0130
• eval_runtime: 1732.3102
• eval_samples_per_second: 0.451
• eval_steps_per_second: 0.028
• epoch: 7.0
• step: 1372

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: 0.001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 2000
• mixed_precision_training: Native AMP

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.41.0.dev0
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.19.1