speech31/wav2vec2-large-english-TIMIT-phoneme_v3

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

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
• —trainbatchsize: 32
• —evalbatchsize: 16
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 1000
• —num_epochs: 50
• —mixedprecisiontraining: 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