metadata

license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - generated_from_trainer
model-index:
  - name: asr-amharic-phoneme-based-37-6
    results: []

asr-amharic-phoneme-based-37-6

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: 0.2492
eval_wer: 0.2974
eval_phoneme_cer: 0.0554
eval_cer: 0.0798
eval_runtime: 24.1249
eval_samples_per_second: 14.881
eval_steps_per_second: 1.865
epoch: 46.37
step: 37000

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: 3e-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: 100
num_epochs: 50

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1