metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
model-index:
  - name: wav2vec2-base-cv-corpus
    results: []

wav2vec2-base-cv-corpus

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

eval_loss: 2.9772
eval_wer: 1.0
eval_runtime: 20.3944
eval_samples_per_second: 16.72
eval_steps_per_second: 2.108
epoch: 2.61
step: 2000

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: 4
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 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2