Whisper Small Vietnamese ver1.1 - Son Huynh
This model is a fine-tuned version of openai/whisper-small on the vivos-train dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1925
- eval_wer: 15.6566
- eval_runtime: 498.9405
- eval_samples_per_second: 1.523
- eval_steps_per_second: 0.19
- epoch: 0.27
- step: 200
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- training_steps: 800
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0
- Datasets 2.7.1
- Tokenizers 0.12.1
- Downloads last month
- 8