metadata
language:
- zh
license: apache-2.0
base_model: openai/whisper-small
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
metrics:
- wer
model-index:
- name: Whisper Small Chinese-Mandarin
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_16_0 zh-CN
type: mozilla-foundation/common_voice_16_0
config: zh-CN
split: test
args: zh-CN
metrics:
- name: Wer
type: wer
value: 77.85993910395824
Whisper Small Chinese-Mandarin
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_16_0 zh-CN dataset. It achieves the following results on the evaluation set:
- Loss: 0.3738
- Wer: 77.8599
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: 5e-07
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7234 | 1.06 | 500 | 0.4390 | 82.2706 |
| 0.5601 | 3.0 | 1000 | 0.3994 | 80.4089 |
| 0.6714 | 4.06 | 1500 | 0.3857 | 79.6694 |
| 0.4956 | 6.0 | 2000 | 0.3784 | 78.1383 |
| 0.6296 | 7.06 | 2500 | 0.3751 | 78.4863 |
| 0.4632 | 9.0 | 3000 | 0.3738 | 77.8599 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0