speech31/wav2vec2-large-english-TIMIT-phoneme_v3

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

Training Loss	Epoch	Step	Validation Loss	Per
2.2678	6.94	500	0.2347	0.0874
0.25	13.88	1000	0.3358	0.1122
0.2126	20.83	1500	0.3865	0.1131
0.1397	27.77	2000	0.4162	0.1085
0.0916	34.72	2500	0.4429	0.1086
0.0594	41.66	3000	0.3697	0.0987

Framework versions

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