metadata

language:
  - te
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - INDIC_SUPERB_MUCS_OPENSLR
metrics:
  - wer
model-index:
  - name: Swecha Gonthuka - Limited Release
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Crowed sourced dataset
          type: INDIC SUPERB, MUCS, OPENSLR
          config: None
          split: None
          args: 'config: te, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 28.59758159493464

Whisper Small Telugu - Naga Budigam

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

Loss: 0.0768
Wer: 28.5976

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 3000
training_steps: 10000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0729	1.08	5000	0.0934	33.3306
0.0519	2.16	10000	0.0768	28.5976

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0
Datasets 2.7.1
Tokenizers 0.13.2