Edit model card

wav2vec2-conformer-rel-pos-large-speech-commands

This model is a fine-tuned version of facebook/wav2vec2-conformer-rel-pos-large on the speech_commands dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.5969
  • eval_accuracy: 0.9678
  • eval_runtime: 128.1995
  • eval_samples_per_second: 77.863
  • eval_steps_per_second: 1.217
  • epoch: 9.98
  • step: 3310

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: 1e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.7.dev0
  • Tokenizers 0.14.1
Downloads last month
3

Finetuned from

Dataset used to train aryamtos/wav2vec2-conformer-rel-pos-large-speech-commands