xiaoming-leza's picture
update model card README.md
46a72b4
|
raw
history blame
2.86 kB
metadata
language:
  - tr
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - automatic-speech-recognition
  - common_voice
  - generated_from_trainer
datasets:
  - common_voice
metrics:
  - wer
model-index:
  - name: wav2vec2-common_voice-tr-demo
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: COMMON_VOICE - TR
          type: common_voice
          config: tr
          split: test
          args: 'Config: tr, Training split: train+validation, Eval split: test'
        metrics:
          - name: Wer
            type: wer
            value: 0.34950464712491064

wav2vec2-common_voice-tr-demo

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

  • Loss: 0.3828
  • Wer: 0.3495

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: 0.0003
  • 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: 15.0

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.92 100 3.5826 1.0
No log 1.83 200 3.0218 0.9999
No log 2.75 300 0.8985 0.8036
No log 3.67 400 0.5992 0.6197
3.1629 4.59 500 0.4968 0.5340
3.1629 5.5 600 0.4646 0.5045
3.1629 6.42 700 0.4316 0.4425
3.1629 7.34 800 0.4500 0.4735
3.1629 8.26 900 0.4114 0.4123
0.2226 9.17 1000 0.4162 0.4019
0.2226 10.09 1100 0.3999 0.3824
0.2226 11.01 1200 0.4048 0.3842
0.2226 11.93 1300 0.3789 0.3602
0.2226 12.84 1400 0.4024 0.3536
0.1015 13.76 1500 0.3899 0.3575
0.1015 14.68 1600 0.3802 0.3490

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.0
  • Tokenizers 0.13.3