gemini_whisper_ipa

Fine-tuned openai/whisper-small for Santali IPA/Sanlish transliteration (speech-to-text).

Last updated: 2026-08-29T23:56:15.284469Z — after epoch 20.0

Dataset split (80/10/10)

  • train: 1547
  • validation: 193
  • test: 194

Latest evaluation metrics (epoch 20.0)

  • test_loss: 0.4051657021045685
  • test_wer: 40.782828282828284

Training hyperparameters

  • per_device_train_batch_size: 8
  • gradient_accumulation_steps: 2
  • effective_batch_size: 16
  • learning_rate: 0.0001
  • warmup_steps: 100
  • num_train_epochs: 20
  • gradient_checkpointing: True
  • fp16: True
  • eval_strategy: IntervalStrategy.EPOCH
  • save_strategy: SaveStrategy.EPOCH
  • save_total_limit: 2
  • load_best_model_at_end: True
  • metric_for_best_model: wer
  • predict_with_generate: True
  • generation_max_length: 225
Downloads last month
236
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for thunderboltc/gemini_whisper_ipa

Finetuned
(3743)
this model