wav2vec2-xls-r-300m-ja-phoneme_cv_14_3

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the audiofolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7558
  • Wer: 0.1461

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Wer
5.2909 0.44 400 2.8888 1.0
1.7369 0.88 800 0.7558 0.1461

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.3
  • Tokenizers 0.13.3
Downloads last month
103
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_3

Finetuned
(581)
this model
Finetunes
1 model

Evaluation results