Whisper Base Jyutping without Tones Full Version trained with extra data from Common Voice zh-HK
This model is a fine-tuned version of AlienKevin/whisper-base-jyutping-without-tones-full on the Common Voice 14.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0949
- Wer: 9.7694
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- training_steps: 2400
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0921 | 0.14 | 800 | 0.1049 | 10.4769 |
| 0.0824 | 0.28 | 1600 | 0.0989 | 9.8173 |
| 0.0611 | 0.42 | 2400 | 0.0949 | 9.7694 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.