Downloads · 30 days
372
35% of all-time downloads
gemini_whisper_sanlish
thunderboltc/gemini_whisper_sanlish
gemini_whisper_sanlish is a automatic speech recognition model from thunderboltc. Use it when you need speech turned into text.
Fine-tuned openai/whisper-small for Santali IPA/Sanlish transliteration (speech-to-text).
All-time downloads
1.1K
Public
Parameters
242M
13.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Model type
- whisper
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026
- SHA
- f78236f4
Base models
Model card
From the Hugging Face model README
gemini_whisper_ipa
Fine-tuned openai/whisper-small for Santali IPA/Sanlish transliteration (speech-to-text).
Last updated: 2026-08-30T04:53:30.291684Z — after epoch 10.0
Dataset split (80/10/10)
- train: 1547
- validation: 193
- test: 194
Latest evaluation metrics (epoch 10.0)
- test_loss: 0.9323491454124451
- test_wer: 34.66981132075472
- test_cer: 8.268111579369858
Training hyperparameters
- per_device_train_batch_size: 8
- gradient_accumulation_steps: 2
- effective_batch_size: 16
- learning_rate: 3e-05
- warmup_steps: 100
- num_train_epochs: 10
- 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
- Task
- Automatic Speech Recognition
- Type
- whisper
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026