metadata

license: mit
base_model: facebook/w2v-bert-2.0
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: only_head_const_lr_1-e4
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: hy-AM
          split: test
          args: hy-AM
        metrics:
          - name: Wer
            type: wer
            value: 0.9999698904010599

only_head_const_lr_1-e4

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 2.7371
Wer: 1.0000
Cer: 0.8540

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: 0.0001
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: constant
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
9.1084	1.5385	500	9.3283	1.5175	0.7359
4.8706	3.0769	1000	5.0357	1.0044	0.8964
3.8282	4.6154	1500	3.8866	0.9999	0.9809
3.1519	6.1538	2000	3.1656	0.9998	0.9309
2.8747	7.6923	2500	2.8780	1.0002	0.8692
2.7465	9.2308	3000	2.7371	1.0000	0.8540

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1