Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wav2vec2-large-xls-r-300m-kor-11385-3 – AI Model by teddy322 | AlphaNeural AI
You can deploy this model and start earning money today!
teddy322
/
wav2vec2-large-xls-r-300m-kor-11385-3
like
0
transformers
pytorch
tensorboard
wav2vec2
automatic-speech-recognition
generated_from_trainer
zeroth_korean_asr
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
wav2vec2-large-xls-r-300m-kor-11385-3
This model is a fine-tuned version of
teddy322/wav2vec2-large-xls-r-300m-kor-11385-2
on the zeroth_korean_asr dataset. It achieves the following results on the evaluation set:
eval_loss: 0.2425
eval_wer: 0.1495
eval_runtime: 137.8001
eval_samples_per_second: 3.316
eval_steps_per_second: 0.421
epoch: 10.59
step: 3600
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 20
mixed_precision_training: Native AMP
Framework versions
Transformers 4.11.3
Pytorch 1.10.0+cu113
Datasets 1.18.3
Tokenizers 0.10.3
