openai/whisper-small-Assamese
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7523
- Wer: 42.1075
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2518 | 20.01 | 250 | 0.5376 | 143.3410 |
| 0.0069 | 41.01 | 500 | 0.6409 | 49.9268 |
| 0.0004 | 62.01 | 750 | 0.7344 | 43.4455 |
| 0.0001 | 83.0 | 1000 | 0.7523 | 42.1075 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 4
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.