metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
model-index:
  - name: asr-amharic-phoneme-based-39-2
    results: []

asr-amharic-phoneme-based-39-2

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: 0.2977
eval_wer: 0.1056
eval_cer: 0.0538
eval_runtime: 22.8205
eval_samples_per_second: 15.731
eval_steps_per_second: 1.972
epoch: 19.41
step: 6600

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: 5e-05
train_batch_size: 32
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

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0