Hugging Face's logo

vutankiet2901
/
wav2vec2-xls-r-1b-ja

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Japanese
wav2vec2
common-voice
hf-asr-leaderboard
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Metrics Community
wav2vec2-xls-r-1b-ja / README.md
vutankiet2901's picture
vutankiet2901
update model card README.md
fa186b7
preview code
|
raw history blame
No virus
1.42 kB
metadata
language:
  - ja
license: apache-2.0
tags:
  - automatic-speech-recognition
  - mozilla-foundation/common_voice_8_0
  - generated_from_trainer
model-index:
  - name: wav2vec2-xls-r-1b-ja
    results: []

wav2vec2-xls-r-1b-ja

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - JA dataset. It achieves the following results on the evaluation set:

  • Loss: 3.2691
  • Wer: 0.9960
  • Cer: 0.9555

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 2.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.16.0.dev0
  • Pytorch 1.10.1+cu102
  • Datasets 1.18.3
  • Tokenizers 0.11.0