metadata

base_model: mattbonnell/wav2vec2-base-wonders-phonemes
datasets:
  - transcribed_calls
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: wav2vec2-base-wonders-phonemes
    results: []

wav2vec2-base-wonders-phonemes

This model is a fine-tuned version of mattbonnell/wav2vec2-base-wonders-phonemes on the transcribed_calls dataset.

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: 2
seed: 42
distributed_type: multi-GPU
num_devices: 6
gradient_accumulation_steps: 2
total_train_batch_size: 384
total_eval_batch_size: 12
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.01
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.44.0
Pytorch 2.4.0+cu124
Datasets 2.21.0
Tokenizers 0.19.1