Hubert-noisy-ft-eval

This model is a fine-tuned version of utakumi/Hubert-noisy_common_voice_debug on the ORIGINAL_NOISY_COMMON_VOICE - JA dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.1085
• eval_model_preparation_time: 0.0093
• eval_wer: 1.0
• eval_cer: 0.3247
• eval_runtime: 152.9105
• eval_samples_per_second: 32.444
• eval_steps_per_second: 4.061
• step: 0

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 12500
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3