Whisper Medium Lithuanian CV11
This model is a fine-tuned version of openai/whisper-large on the mozilla-foundation/common_voice_11_0 lt dataset. It achieves the following results on the evaluation set:
- Loss: 0.354951
- Wer: 20.446244
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0056 | 9.42 | 1000 | 0.3252 | 20.5534 |
| 0.0023 | 18.8 | 2000 | 0.3549 | 20.4462 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 17
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.
Dataset used to train DeividasM/whisper-medium-lt
Spaces using DeividasM/whisper-medium-lt 2
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0self-reported20.446