Whisper Small Combined
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1934
- Wer Ortho: 0.2322
- Wer: 0.1353
Model description
This is a fine tunned on merged datasets Common Voice 13 + Fleurs + Juzne vesti (South news)
Rupnik, Peter and Ljubešić, Nikola, 2022,
ASR training dataset for Serbian JuzneVesti-SR v1.0, Slovenian language resource repository CLARIN.SI, ISSN 2820-4042,
http://hdl.handle.net/11356/1679.
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.4708 | 0.48 | 500 | 0.2275 | 0.2704 | 0.1738 |
| 0.4678 | 0.95 | 1000 | 0.1979 | 0.24 | 0.1457 |
| 0.3271 | 1.43 | 1500 | 0.1934 | 0.2322 | 0.1353 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 12
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 Sagicc/whisper-small-sr-combined
Base model
openai/whisper-small