metadata
language:
- nan
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
model-index:
- name: Whisper Small nan-tw - Taiwanese
results: []
Whisper Small nan-tw - Taiwanese
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3647
- Cer: 28.4585
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: 16
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.6816 | 0.65 | 1000 | 0.6212 | 43.9508 |
| 0.3575 | 1.29 | 2000 | 0.4729 | 34.6632 |
| 0.2899 | 1.94 | 3000 | 0.4043 | 31.3601 |
| 0.1543 | 2.58 | 4000 | 0.3714 | 28.9896 |
| 0.087 | 3.23 | 5000 | 0.3647 | 28.4585 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2