Joshua-Abok/finetuning-wav2vec-lora-large-swahili-asr-model_v20

<!-- 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. -->

finetuning-wav2vec-lora-large-swahili-asr-model_v20

This model is a fine-tuned version of Joshua-Abok/finetuning-wav2vec-large-swahili-asr-model_v10 on the commonvoice13_0 dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.3743
• —eval_wer: 0.2301
• —eval_runtime: 625.6728
• —evalsamplesper_second: 18.014
• —evalstepsper_second: 2.252
• —epoch: 1.94
• —step: 2800

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: 0.0003
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —num_epochs: 30
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.36.0.dev0
• —Pytorch 2.0.1+cu118
• —Datasets 2.14.7
• —Tokenizers 0.15.0