whisper-large-v3-finetuned

This model is a fine-tuned version of openai/whisper-large-v3 on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.5676
• eval_wer: 29.3023
• eval_runtime: 128.1141
• eval_samples_per_second: 0.156
• eval_steps_per_second: 0.023
• epoch: 9.1
• step: 30

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: 8
• eval_batch_size: 8
• 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: 30
• mixed_precision_training: Native AMP

Framework versions

• PEFT 0.11.1
• Transformers 4.42.3
• Pytorch 2.4.0
• Datasets 2.19.2
• Tokenizers 0.19.1