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

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: 0.6722
• Wer: 0.7398

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-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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_ratio: 0.2
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.3543	0.6024	153	0.9139	0.8117
0.7847	1.2047	306	0.7780	0.7863
0.6806	1.8071	459	0.7048	0.7508
0.6958	2.4094	612	0.6722	0.7398

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu121
• Datasets 2.17.1
• Tokenizers 0.21.0