metadata

license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - generated_from_trainer
model-index:
  - name: wav2vec2-base-timit-demo
    results: []

wav2vec2-base-timit-demo

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

eval_loss: nan
eval_cer: 0.9937
eval_runtime: 130.5666
eval_samples_per_second: 12.867
eval_steps_per_second: 1.608
epoch: 3.46
step: 500

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: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 50

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.2.dev0
Tokenizers 0.15.0