Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
wav2vec2-bert-armenian-cv17 – AI Model by Codename324 | AlphaNeural AI
You can deploy this model and start earning money today!
Codename324
/
wav2vec2-bert-armenian-cv17
like
0
transformers
tensorboard
safetensors
wav2vec2-bert
automatic-speech-recognition
generated_from_trainer
facebook/w2v-bert-2.0
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
wav2vec2-bert-armenian-cv17
This model is a fine-tuned version of
facebook/w2v-bert-2.0
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.1812
Wer: 0.2141
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use OptimizerNames.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: 50
num_epochs: 2
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
2.4576
0.5333
100
0.3531
0.4098
0.2684
1.064
200
0.2276
0.2703
0.1681
1.5973
300
0.1812
0.2141
Framework versions
Transformers 4.53.1
Pytorch 2.6.0+cu124
Datasets 2.16.1
Tokenizers 0.21.2
