whisper-hindi-base
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4967
- Wer: 52.9617
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: 1.75e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3969 | 0.9 | 250 | 0.5607 | 60.9756 |
| 0.2526 | 1.8 | 500 | 0.5176 | 57.1429 |
| 0.156 | 2.7 | 750 | 0.5061 | 53.7979 |
| 0.1031 | 3.6 | 1000 | 0.4967 | 52.9617 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 21
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.