metadata

library_name: transformers
language:
  - te
base_model: openai/whisper-small-v3
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper Small Te - Prashanth Kattoju
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17
          type: mozilla-foundation/common_voice_17_0
          config: te
          split: test
          args: te
        metrics:
          - name: Wer
            type: wer
            value: 15.384615384615385

Whisper Small Te - Prashanth Kattoju

This model is a fine-tuned version of openai/whisper-small-v3 on the Common Voice 17 dataset. It achieves the following results on the evaluation set:

Loss: 0.0903
Wer Ortho: 40.6593
Wer: 15.3846

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0106	8.6207	1000	0.0903	40.6593	15.3846

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1

Future Scope

More training need to done with generalized data for more accurate results