Whisper Small 3Lang 1 token only
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.7394
- eval_cer: 21.6707
- eval_wer: 34.9815
- eval_both_er: 29.2571
- eval_LID: 100.0
- eval_total: 29.2571
- eval_runtime: 5490.853
- eval_samples_per_second: 17.277
- eval_steps_per_second: 1.08
- epoch: 6.0794
- step: 162000
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: 4
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- 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: 500
- training_steps: 240000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 9
Model tree for JunWorks/whisper-small-3lang1token-4090-omitToken-customData
Base model
openai/whisper-small