metadata
language:
- zh
license: apache-2.0
tags:
- generated_from_trainer
base_model: openai/whisper-tiny
datasets:
- mozilla-foundation/common_voice_16_1
model-index:
- name: Whisper Tiny chinese - VingeNie
results: []
Whisper Tiny chinese - VingeNie
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7856
- Cer Ortho: 36.1208
- Cer: 32.0924
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 25
- training_steps: 2400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer |
|---|---|---|---|---|---|
| 1.0023 | 0.0899 | 225 | 1.0604 | 58.8669 | 38.7306 |
| 0.9338 | 0.1799 | 450 | 1.0007 | 55.0375 | 37.7216 |
| 0.9892 | 0.2698 | 675 | 0.9449 | 45.2119 | 36.3744 |
| 0.9126 | 0.3597 | 900 | 0.9045 | 45.4458 | 35.1969 |
| 0.858 | 0.4496 | 1125 | 0.8924 | 55.0433 | 35.0772 |
| 0.7692 | 0.5396 | 1350 | 0.8679 | 37.4430 | 33.7125 |
| 0.7732 | 0.6295 | 1575 | 0.8436 | 40.0120 | 33.3513 |
| 0.806 | 0.7194 | 1800 | 0.8117 | 41.9431 | 33.0564 |
| 0.8153 | 0.8094 | 2025 | 0.7962 | 47.2879 | 31.8011 |
| 0.7918 | 0.8993 | 2250 | 0.7856 | 36.1208 | 32.0924 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.0.1+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1