whisper-small bengali
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1069
- eval_wer_ortho: 0.3909
- eval_wer: 0.1697
- eval_runtime: 31948.7278
- eval_samples_per_second: 0.926
- eval_steps_per_second: 0.463
- epoch: 0.1
- step: 1500
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: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 1