Whisper Medium CodeMixed bn-en - Mohammad Fayez Ullah
This model is a fine-tuned version of openai/whisper-medium on the Custom dataset: CodeMixed-BanEng dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1913
- eval_wer: 40.7018
- eval_runtime: 519.0489
- eval_samples_per_second: 0.605
- eval_steps_per_second: 0.152
- epoch: 61.3208
- step: 6500
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: 12
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 12000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.41.1
- Pytorch 2.2.1
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for fayez94/whisper-medium_AcodeMixed_ASR
Base model
openai/whisper-medium