wav2vec2-base-gumbelVQ-timit-fine-tuned

This model is a fine-tuned version of wav2vec2-pretrained-base-gumbelVQ on the TIMIT_ASR - NA dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7549
  • Wer: 0.4902

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 20.0

Training results

Training Loss Epoch Step Validation Loss Wer
0.4628 10.0 1450 0.6779 0.5171
0.3036 20.0 2900 0.7549 0.4902

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.3.0.dev20231229+cu118
  • Datasets 2.16.0
  • Tokenizers 0.15.0
Downloads last month
17
Safetensors
Model size
94.4M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train subatomicseer/wav2vec2-base-gumbelVQ-timit-fine-tuned

Evaluation results