metadata

language:
  - ta
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Tiny Tamil Language
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: ta
          split: invalidated
          args: 'config: ta, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 165.71071141953453

Whisper Tiny Tamil Language

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: 0.8516
Wer: 165.7107

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: 8
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
0.4891	0.17	250	0.9969	186.2744
0.4055	0.34	500	0.9090	181.1712
0.3845	0.51	750	0.8615	178.4639
0.3556	0.68	1000	0.8516	165.7107

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1