KapilPathak's picture
End of training
bdac67c verified
metadata
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
  - generated_from_trainer
datasets:
  - common_voice_6_1
metrics:
  - wer
model-index:
  - name: wav2vec2-large-mms-1b-turkish-colab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_6_1
          type: common_voice_6_1
          config: tr
          split: test
          args: tr
        metrics:
          - name: Wer
            type: wer
            value: 0.22030436114799307

wav2vec2-large-mms-1b-turkish-colab

This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_6_1 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1538
  • Wer: 0.2203

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: 32
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
3.6379 0.92 100 0.1794 0.2436
0.2808 1.83 200 0.1671 0.2387
0.2646 2.75 300 0.1606 0.2228
0.2413 3.67 400 0.1538 0.2203

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.2.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2