README.md

metadata

license: apache-2.0
base_model: jonatasgrosman/wav2vec2-large-xlsr-53-japanese
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: my_jp_asr_cv13_model
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: ja
          split: None
          args: ja
        metrics:
          - name: Wer
            type: wer
            value: 0.875

my_jp_asr_cv13_model

This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-japanese on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 3.1772
• Cer: 0.3512
• Wer: 0.875

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
0.16	250.0	1000	3.1440	0.3223	0.875
0.1061	500.0	2000	3.1772	0.3512	0.875

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1