Edit model card

Visualize in Weights & Biases

wav2vec2-960h-fine-tuning-2

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9325
  • Wer: 11.2741

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: 4e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.9935 76 1.3301 15.9156
No log 2.0 153 3.8761 17.1732
No log 2.9935 229 1.8980 13.3403
No log 3.9739 304 0.9325 11.2741

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
2
Safetensors
Model size
94.4M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for ashe194/wav2vec2-facebook-ft-combined_4gram

Finetuned
(119)
this model