asr2

This model is a fine-tuned version of GodsonNtungi/asr2 on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2567
• eval_wer: 0.2528
• eval_runtime: 6.694
• eval_samples_per_second: 20.914
• eval_steps_per_second: 2.689
• epoch: 3.23
• step: 700

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
• train_batch_size: 32
• eval_batch_size: 8
• 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: 100
• training_steps: 1500
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.1
• Datasets 1.18.3
• Tokenizers 0.14.1