w2v-bert-kannada_new_v3

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1652
• eval_wer: 0.2279
• eval_runtime: 798.2629
• eval_samples_per_second: 5.84
• eval_steps_per_second: 5.84
• epoch: 0.9054
• step: 14000

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: 4e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 5
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.41.1
• Pytorch 2.1.2+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1