Fixed whisper models
Collection
Custom whisper models found in the wild, updated to the proper generation config. • 5 items • Updated
Whisper Medium Slovak CV11
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 sk dataset. It achieves the following results on the evaluation set:
- Loss: 0.3982
- Wer: 23.1437
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: 64
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.001 | 14.29 | 1000 | 0.3982 | 23.1437 |
| 0.0013 | 28.57 | 2000 | 0.4343 | 24.0362 |
| 0.0001 | 42.86 | 3000 | 0.4565 | 23.3222 |
| 0.0001 | 57.14 | 4000 | 0.4700 | 23.3936 |
| 0.0001 | 71.43 | 5000 | 0.4753 | 23.4531 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Collection including faur-ai/whisper-medium-sk-cv11
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 sktest set self-reported23.144