kojo-george/asr_model

<!-- 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. -->

asr_model

This model is a fine-tuned version of facebook/mms-1b-all on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 1.3621
• —eval_wer: 0.3900
• —eval_runtime: 58.7393
• —evalsamplesper_second: 4.75
• —evalstepsper_second: 0.596
• —epoch: 0.895
• —step: 1790

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: 0.001
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 100
• —training_steps: 2000
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.42.0.dev0
• —Pytorch 2.3.0+cu121
• —Datasets 2.19.2
• —Tokenizers 0.19.1