whisper-medium-cantonese
This model is a fine-tuned version of openai/whisper-medium on the thisiskeithkwan/canto dataset. It achieves the following results on the evaluation set:
- Loss: 0.4767
- Cer: 1.2115
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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.5362 | 0.76 | 500 | 0.4981 | 1.5560 |
| 0.3313 | 1.52 | 1000 | 0.4767 | 1.2115 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3
- Downloads last month
- 75
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for thisiskeithkwan/whisper-medium-1000steps-spaced
Base model
openai/whisper-medium