Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use powervel/whisper-small-dv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use powervel/whisper-small-dv with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="powervel/whisper-small-dv")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("powervel/whisper-small-dv") model = AutoModelForSpeechSeq2Seq.from_pretrained("powervel/whisper-small-dv") - Notebooks
- Google Colab
- Kaggle
whisper-small-dv
This model is a fine-tuned version of openai/whisper-small on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2256
- Wer Ortho: 36.7208
- Wer: 12.2160
Model description
This is the small variant of Whisper model.
Intended uses & limitations
Fine Tuned on the tamil split of Fleurs hence Made for Tamil ASR
Training and evaluation data
Not so Great, trained on Google Colab
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0502 | 4.2373 | 500 | 0.2256 | 36.7208 | 12.2160 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4
- Downloads last month
- -
Model tree for powervel/whisper-small-dv
Base model
openai/whisper-smallEvaluation results
- Wer on fleursself-reported12.216