whisper-tiny-zh-tw / README.md
leowang707's picture
End of training
693ea6a verified
---
license: apache-2.0
base_model: Wellyowo/whisper-tiny-zh-tw
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: whisper-tiny-zh-tw
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: zh-TW
split: test
args: zh-TW
metrics:
- name: Wer
type: wer
value: 60.19417475728155
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-tiny-zh-tw
This model is a fine-tuned version of [Wellyowo/whisper-tiny-zh-tw](https://huggingface.co/Wellyowo/whisper-tiny-zh-tw) on the common_voice_13_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5537
- Wer Ortho: 59.0
- Wer: 60.1942
## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
| 0.0079 | 0.6882 | 500 | 0.5537 | 59.0 | 60.1942 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1