metadata
language:
- zh
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
model-index:
- name: whispertest
results: []
whispertest
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2991
- Wer: 167.4731
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2588 | 0.4 | 1000 | 0.2991 | 167.4731 |
| 0.275 | 0.81 | 2000 | 0.2991 | 167.4731 |
| 0.2793 | 1.21 | 3000 | 0.2991 | 167.4731 |
| 0.2511 | 1.61 | 4000 | 0.2991 | 167.4731 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3