whisper-large-v2-finetuned

This model is a fine-tuned version of openai/whisper-large-v2 on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.3976
• eval_wer: 102.8686
• eval_runtime: 329.5091
• eval_samples_per_second: 0.492
• eval_steps_per_second: 0.012
• epoch: 125.0
• step: 1000

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: 0.0001
• train_batch_size: 50
• eval_batch_size: 50
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 10
• training_steps: 1000
• mixed_precision_training: Native AMP

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.2.2+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1