Whisper Medium - Malayalam
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2084
- eval_wer: 71.3595
- eval_runtime: 761.8206
- eval_samples_per_second: 0.932
- eval_steps_per_second: 0.117
- epoch: 4.7244
- step: 600
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 1000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- -
Model tree for Abdulvajid/whisper-medium-ml
Base model
openai/whisper-medium