Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wav2vec2-final-learning-rate-3e-4_batch-size-64 – AI Model by kaarthu2003 | AlphaNeural AI
You can deploy this model and start earning money today!
kaarthu2003
/
wav2vec2-final-learning-rate-3e-4_batch-size-64
like
0
transformers
safetensors
wav2vec2
automatic-speech-recognition
generated_from_trainer
facebook/wav2vec2-large-xlsr-53
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
wav2vec2-final-learning-rate-3e-4_batch-size-64
This model is a fine-tuned version of
facebook/wav2vec2-large-xlsr-53
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: inf
Wer: 0.4688
Cer: 0.1134
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: 64
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 400
num_epochs: 20
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
Cer
6.1161
4.3478
400
inf
0.9999
0.9996
1.1843
8.6957
800
inf
0.5154
0.1291
0.372
13.0435
1200
inf
0.4815
0.1215
0.2312
17.3913
1600
inf
0.4688
0.1134
Framework versions
Transformers 4.51.1
Pytorch 2.1.0+cu118
Datasets 3.5.0
Tokenizers 0.21.1
