metadata
library_name: transformers
language:
- zhc
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Base zh-CN - fzuhyz
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: zhc
split: test
args: 'config: zhc, split: test'
metrics:
- name: Wer
type: wer
value: 85.85000000000001
Whisper Base zh-CN - fzuhyz
This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5922
- Wer: 85.8500
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: 1
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | Wer |
|---|---|---|---|---|
| 0.6972 | 0.8 | 1000 | 0.6448 | 88.8 |
| 0.5154 | 1.6 | 2000 | 0.6052 | 87.45 |
| 0.4207 | 2.4 | 3000 | 0.5945 | 86.3 |
| 0.353 | 3.2 | 4000 | 0.5935 | 85.45 |
| 0.3437 | 4.0 | 5000 | 0.5922 | 85.8500 |
Framework versions
- Transformers 4.52.3
- Pytorch 2.6.0+cu118
- Datasets 2.16.0
- Tokenizers 0.21.1