whisper-tiny-tamil-telugu

This model is a fine-tuned version of openai/whisper-tiny on the Speech Commands dataset. It achieves the following results on the evaluation set:

  • Loss: nan
  • Accuracy: 0.0682

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: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • 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: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.7103 1.0 175 1.7471 0.3182
1.7409 2.0 350 1.7368 0.1818
1.8159 3.0 525 1.7274 0.2955
1.7017 4.0 700 1.7233 0.2955
1.7597 5.0 875 1.7177 0.2955
1.7603 6.0 1050 1.7123 0.2955
1.6626 7.0 1225 1.7082 0.2955
1.5964 8.0 1400 nan 0.25
0.0 9.0 1575 nan 0.0682
0.0 10.0 1750 nan 0.0682

Framework versions

  • Transformers 4.48.0.dev0
  • Pytorch 2.2.2
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
24
Safetensors
Model size
8.31M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for JasHugF/whisper-tiny-tamil-telugu

Finetuned
(1283)
this model

Evaluation results