Baybars's picture
update model card README.md
56c12f3
|
raw
history blame
1.73 kB
metadata
language:
  - tr
tags:
  - automatic-speech-recognition
  - common_voice
  - generated_from_trainer
datasets:
  - common_voice
model-index:
  - name: ''
    results: []

This model is a fine-tuned version of hf-test/xls-r-dummy on the COMMON_VOICE - TR dataset. It achieves the following results on the evaluation set:

  • Loss: 59.6880
  • Wer: 1.0

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: 5.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.92 100 149.2460 1.0032
No log 1.83 200 135.3586 1.0
No log 2.75 300 114.3390 1.0
No log 3.67 400 88.3077 1.0
67.8005 4.59 500 64.6167 1.0

Framework versions

  • Transformers 4.17.0.dev0
  • Pytorch 1.10.2+cu102
  • Datasets 1.18.2.dev0
  • Tokenizers 0.11.0