Whisper Small new-ru-pl-bg AIIA
This model is a fine-tuned version of Maks545curve/whisper-small-new-ru-pl-a on the Common Voice 17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4125
- Wer Ortho: 30.7445
- Wer: 24.0835
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 70
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3229 | 2.1008 | 500 | 0.3644 | 29.8090 | 23.6728 |
| 0.0447 | 4.2017 | 1000 | 0.4125 | 30.7445 | 24.0835 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cpu
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 8
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 Maks545curve/whisper-small-new-ru-pl-bg-a
Base model
openai/whisper-small
Finetuned
Maks545curve/whisper-small-new-ru-a
Finetuned
Maks545curve/whisper-small-new-ru-pl-a