metadata
language: ja
datasets:
- common_voice
metrics:
- wer
tags:
- audio
- automatic-speech-recognition
- speech
- xlsr-fine-tuning-week
license: apache-2.0
model-index:
- name: wav2vec2-live-japanese
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice Japanese
type: common_voice
args: ja
metrics:
- name: Test WER
type: wer
value: 22.08%
- name: Test CER
type: cer
value: 10.08%
wav2vec2-live-japanese
https://github.com/ttop32/wav2vec2-live-japanese-translator
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the
- common_voice
- JSUT
- CSS10
- TEDxJP-10K
- JVS
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: 0.0003
- train_batch_size: 3
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 50
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.10.0
- Pytorch 1.9.1
- Datasets 1.11.0
- Tokenizers 0.10.3