metadata
library_name: peft
language:
- bn
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: Whisper Small Hi - Tanjin Alam
results: []
Whisper Small Hi - Tanjin Alam
This model is a fine-tuned version of openai/whisper-base on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1459
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: 0.001
- train_batch_size: 8
- 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: 50
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.228 | 1.0 | 3820 | 0.2333 |
| 0.1672 | 2.0 | 7640 | 0.1747 |
| 0.123 | 3.0 | 11460 | 0.1459 |
Framework versions
- PEFT 0.13.3.dev0
- Transformers 4.45.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3