metadata
library_name: transformers
language:
- zh
license: apache-2.0
base_model: openai/whisper-small
tags:
- whisper
- cantonese
- zh-hk
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: whisper-small-zh-hk
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: zh-HK
split: None
args: 'config: zh-HK, split: train'
metrics:
- name: Wer
type: wer
value: 200.48085485307215
whisper-small-zh-hk
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2332
- Wer: 200.4809
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: 8
- eval_batch_size: 8
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3422 | 0.5708 | 1000 | 0.3029 | 237.3286 |
| 0.1806 | 1.1416 | 2000 | 0.2574 | 181.2467 |
| 0.1626 | 1.7123 | 3000 | 0.2383 | 171.2199 |
| 0.0892 | 2.2831 | 4000 | 0.2332 | 200.4809 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3