Whisper tiny Vietnamese ver1.1 - Son Huynh

This model is a fine-tuned version of openai/whisper-small on the common_voice dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.4337
• eval_wer: 61.8094
• eval_runtime: 44.5363
• eval_samples_per_second: 4.446
• eval_steps_per_second: 0.09
• epoch: 71.43
• step: 500

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 56
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 300
• training_steps: 1000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.11.0
• Datasets 2.7.1
• Tokenizers 0.12.1