README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - common_voice
metrics:
  - wer
model-index:
  - name: wavlm-base-plus_zh_tw_ver3
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice
          type: common_voice
          config: zh-TW
          split: test
          args: zh-TW
        metrics:
          - name: Wer
            type: wer
            value: 1

wavlm-base-plus_zh_tw_ver3

This model is a fine-tuned version of microsoft/wavlm-base-plus on the common_voice dataset. It achieves the following results on the evaluation set:

• Loss: 11.5929
• Wer: 1.0

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: 7.5e-05
• train_batch_size: 32
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 6.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
82.628	2.5	500	79.5587	1.0
17.5635	5.0	1000	11.5929	1.0

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 1.12.0+cu102
• Datasets 2.10.1
• Tokenizers 0.13.2