metadata

tags:
  - generated_from_trainer
model-index:
  - name: wav2vec2-large-en-in-lm
    results: []

wav2vec2-large-en-in-lm

This model is a fine-tuned version of crossdelenna/wav2vec2-large-en-in-lm on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 0.1130
eval_wer: 0.1269
eval_runtime: 21.8548
eval_samples_per_second: 7.55
eval_steps_per_second: 0.961
epoch: 10.0
step: 1210

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: 8
eval_batch_size: 8
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: 30
mixed_precision_training: Native AMP

Framework versions

Transformers 4.17.0
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1