Whisper Tiny Hu v3
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2041
- eval_wer_ortho: 13.8474
- eval_wer: 12.7928
- eval_runtime: 1002.1306
- eval_samples_per_second: 4.621
- eval_steps_per_second: 0.578
- epoch: 13.39
- step: 20000
Model description
Hungarian language trained modell. Faster-whisper versions in int8, fp16 and ft32 floders.
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: 4e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 500
- training_steps: 20000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 45
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Hungarians/whisper-tiny-cv16-hu-v3
Base model
openai/whisper-tiny
Finetuned
this model
Dataset used to train Hungarians/whisper-tiny-cv16-hu-v3
Evaluation results
- Wer on Common Voice 16.0 - Hungariantest set self-reported12.793