Hugging Face's logo

leenag
/
W2V2-bert-Malasar

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
W2V2-bert-Malasar / README.md
leenag's picture
leenag
End of training
dcd4d8f verified
preview code
|
raw
history blame contribute delete
1.57 kB
metadata
library_name: transformers
license: mit
base_model: facebook/w2v-bert-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: W2V2-bert-Malasar
    results: []

W2V2-bert-Malasar

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: 2.3938
  • Wer: 1.0533

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • 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
No log 4.6512 100 3.1126 1.0
No log 9.3023 200 2.3938 1.0533

Framework versions

  • Transformers 4.44.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.16.0
  • Tokenizers 0.19.1