metadata

language:
  - te
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - Sonal0205/telugu_whisper_asr
metrics:
  - wer
model-index:
  - name: Whisper Small te - heisenberg3376
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: telugu asr
          type: Sonal0205/telugu_whisper_asr
          args: 'config: te, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 30.053507728894175

Whisper Small te - heisenberg3376

This model is a fine-tuned version of openai/whisper-small on the Sonal0205/telugu_whisper_asr dataset. It achieves the following results on the evaluation set:

Loss: 0.1082
Wer: 30.0535

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: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0923	1.0582	1000	0.1281	43.7277
0.0377	2.1164	2000	0.1060	35.0773
0.0151	3.1746	3000	0.1125	32.5505
0.0063	4.2328	4000	0.1082	30.0535

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1