metadata

license: apache-2.0
base_model: vitouphy/wav2vec2-xls-r-300m-timit-phoneme
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: shared_audio
    results: []

shared_audio

This model is a fine-tuned version of vitouphy/wav2vec2-xls-r-300m-timit-phoneme on the None dataset. It achieves the following results on the evaluation set:

Loss: 66.1707
Wer: 1.2143
Cer: 9.2148

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
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: 1
training_steps: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
58.4649	0.03	2	66.1707	1.2143	9.2148

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2