wav2vec2-base960-english-phoneme_v3

This model is a fine-tuned version of facebook/wav2vec2-large on the TIMIT dataset. It achieves the following results on the evaluation set:

• Loss: 0.3697
• Cer: 0.0987

Training and evaluation data

Training: TIMIT dataset training + validation set Evaluation: TIMIT dataset test set

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.23.0.dev0
• Pytorch 1.12.1.post201
• Datasets 2.5.2.dev0
• Tokenizers 0.12.1