metadata
library_name: transformers
language:
- ta
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper tamil Finetuning-powervel
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: google/fleurs
type: google/fleurs
config: ta_in
split: train
args: ta_in
metrics:
- type: wer
value: 12.267598919434292
name: Wer
Whisper tamil Finetuning-powervel
This model is a fine-tuned version of openai/whisper-small on the google/fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2260
- Wer Ortho: 36.7344
- Wer: 12.2676
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: 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 |
|---|---|---|---|---|---|
| 0.05 | 4.2373 | 500 | 0.2260 | 36.7344 | 12.2676 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4