metadata

license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - generated_from_trainer
datasets:
  - xtreme_s
metrics:
  - wer
model-index:
  - name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod6
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: xtreme_s
          type: xtreme_s
          config: fleurs.id_id
          split: test
          args: fleurs.id_id
        metrics:
          - name: Wer
            type: wer
            value: 0.4653494985780572

wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod6

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the xtreme_s dataset. It achieves the following results on the evaluation set:

Loss: 0.9273
Wer: 0.4653

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: 0.001
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: 600
num_epochs: 120
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.8946	18.18	300	2.8697	1.0
1.0963	36.36	600	0.8022	0.5904
0.1715	54.55	900	0.9387	0.5567
0.0953	72.73	1200	0.9120	0.5082
0.0651	90.91	1500	0.9362	0.4854
0.044	109.09	1800	0.9273	0.4653

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1