Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
w2v-bert-2.0-mongolian-colab-CV16.0 – AI Model by mendeeb | AlphaNeural AI
You can deploy this model and start earning money today!
mendeeb
/
w2v-bert-2.0-mongolian-colab-CV16.0
like
0
transformers
tensorboard
safetensors
wav2vec2-bert
automatic-speech-recognition
generated_from_trainer
common_voice_16_0
facebook/w2v-bert-2.0
finetune
mit
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
w2v-bert-2.0-mongolian-colab-CV16.0
This model is a fine-tuned version of
facebook/w2v-bert-2.0
on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:
Loss: 0.5145
Wer: 0.3210
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: 2
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: 500
num_epochs: 10
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
1.7876
2.3636
300
0.6367
0.5084
0.3434
4.7273
600
0.5483
0.4328
0.1767
7.0870
900
0.5563
0.3709
0.0741
9.4506
1200
0.5145
0.3210
Framework versions
Transformers 4.54.0
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2
