w2v-bert-2.0-Chinese-colab-CV16.0-aishell-ark-gs-vtb-ts-fs

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

• Loss: 0.6568
• Wer: 0.9998

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 128
• total_train_batch_size: 512
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.658	0.9981	180	0.7483	1.0
1.2313	1.9925	360	0.6796	0.9998
1.0232	2.9870	540	0.6568	0.9998

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu121
• Datasets 2.17.1
• Tokenizers 0.21.0