head_l23_cos_anneal_2

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.2120
• eval_wer: 0.9981
• eval_cer: 0.4183
• eval_runtime: 72.4648
• eval_samples_per_second: 59.077
• eval_steps_per_second: 7.397
• epoch: 104.6154
• step: 34000

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 154
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1